From 4eac1b346e7e9db8123c48f2f106bfc9fcad9aa5 Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Sun, 22 Jun 2025 11:45:43 +0800
Subject: [PATCH] wip

---
 .gitignore                          |    4 +
 figs/truthfulqa_Qwen_Qwen3-1.7B.png |  Bin 33182 -> 95288 bytes
 nbs/02b_TQA_regr_w_kv.ipynb         | 1194 +++++++++++----------------
 research_journal.md                 |  281 +++++++
 4 files changed, 754 insertions(+), 725 deletions(-)

diff --git a/.gitignore b/.gitignore
index 6eb1488..d9d2ba6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,7 @@
+claude_temp*.md
+
+data/
+
 # Python-generated files
 __pycache__/
 *.py[oc]
diff --git a/figs/truthfulqa_Qwen_Qwen3-1.7B.png b/figs/truthfulqa_Qwen_Qwen3-1.7B.png
index f55839ff63bae2b0f2eec9da834dcfee9b787d7d..c2dfb712b853e8940bb08fa272aa295e30edf74f 100644
GIT binary patch
literal 95288
zcmb5W2RzsB+cr)+r6CkWA~PeSMUg`GPPVL&WRu-e2-z!=oia*Bl97^CiiVMh$Q~Kl
z{Ew^d|NY$0^W4vW{9fPR>-+i|AMf{do!5CD=W!h8<*%xIhMJ0zih_cIT259<oq}RD
z4Fv^d?S^&u%J$@~TktPYCuwab4ciM&uEq}L6iUWUc9(3OE?JqdxR^UQTG?I}<`+E3
zFUZSc>EvYRC@LUe^PfM#Z|h(o;Ap$ti%;2TC#&N~L9x}C{GalnM1~awB?X0?l%(dB
z_~Gwv`auIfSAL&k|CB1_(i)z}K^?|bB^8w=*L82#LRmp;Uf>2bHThdqp_%(HFbeqz
z>fAo)pQXdN5SP8U-0wQ7k}-W#=kv7Zaq+ujP7Pj0GtS@p-g%A<>DTKGyuQ74@3u9P
z|Nh~k?DZ*Gb)99y-+w&aq|TiBkMG^2*}=5&KYnVPyrR?o|NIrf#?b%!_mkfI|M&&*
zfEr=Gk~bCt8&>%R-(=ZvDzkfVFrci=J9K6D;Y%%?20uGWJp!3e#C<EWRmj!R)y21U
zd)&r4%d5Y9p<`oXYs<HKJyyPw^KqJrX92JA=IvV{&sjS~Ma6?cLdoZH4QJ=(e$W2?
zd8)pyq2X<1<ti^PuZBbkqv3*2pFT}~FaP!a-lt+m3;e4(<;>j)rrmUOX{se<YvknQ
z`iF+XBO=y#E?O8x+*rR==)${Q@7}#TC?fKvt&LGYKwz|^bfI>7rTx#yx9Xx!?*lV!
znHm`}qRu?Oe*Mb7_=W1gfdju95)^cG+sZZTuNxFQ_zIf7{a9$D*H&bE_s*S7Gh>|s
zY77E~FDsgw@><584|`~|tSl}qQI1be*3TFYea(JaP{7X0+MV)^XVI~4=^GtcV)4Y^
zKdVh`Z3UJ}FMk*1H+;#pBypL7nmS13#ar9*rMF3^Z_9fcnwYRQHZ}(Cm0;G;(1<%^
z{YS0YXW<W@Muu|l$E4GncOAUColWLJdb*5*gHTdZl9aUc_FcRDu<m7!cbQMr;dL!P
zKirQ0@fyC=PO=W(ePqj~O`9k>Ub?+5ux`c!{;Z2UaOwLCx~qd<9zXM1aKXQ3)JEn7
zE_S>;hP}$L|M|9}+UJk2&Xe<$-wJI~uoLeRCH5*QDdp%FpVHRerKYAfJ3nt?VlvU1
zGn2W6NmQz@At9~2IoIg!-Md>aT)6P={)u}RzdXVRQ5V{LlPULJ(thE@eZu3<;!f*$
z?EH<c*S9rt4Ntr*Ev<d`?oD;|ZM@PpCZ?cAk1jqnKkhXjfrYAfX5GZL(9u)iK7BDP
zJbd!|j@GBGt*tMw{JxH05%yX3)YR16C1M$JJ)3r!I+<<XhU=;UpC6x78I{!1)4Mm(
zTmR{W^N>%j`buXwrwT=XXSsy)(ATAY2Tw1rV^00shMIG$-@Q|GFFk#G%hXWwU97&4
z+k~0RNSkk5TwHrG-f|ZMLt~}}=c-k!?3|s?J~TaxXD;?=Df9BsJbTvO)wK_Qq<>&w
z$zpV}FEuIYcTs^A7VOfu!XS2qsDpMtP7XNl*s){&&q%#%r&smoOb!1#cT%u0J_=0o
zJc5F1gPzQyPJU+}YYBQUUP)JsWo7!5V<1L;K9E5ee=<!joP&J6-r035LPBAE9};(L
z+jg?IF7jIZ%Hhp>#p64DRuYsGMCshTPn}w&5XIZoTOUnjko#av3IAOk%w+mL?vTi(
z7S++xm(?z#?XeLNw5+VGQfIm)lof4g)<|;QNKQ_+{F=oO8XD>}+!BhHx5vk?%E&}m
zCFSO-xVwvD9iA5#Q=T_BXLlVgaUIhx^E}2R=8}rVJSryUh&^VpsEZtK$uTGqy43RI
zRK}{}7cWe#taQ$o8oj(CX=%x|dfn!bA*mY8$6C}|w{FcbDp%Imk8k%-Nfb9<SzdA)
zX!12Ibq|e=t;I*kU+G&uqoA;ff}Ne6W#uzR>j`m>KfDO)bo2Ts@}nUk+ln2UK7EQk
z;c*zDCSuzWj|e>I@#j)8w{BEal;_IQ%wp%t(%x*{g38ygR|^XZUw9W2nrqnUy};-A
z>s{@PySzNr{QUgzw;~nyk)GOcB#UQ=v4Mi>yL&(7TWNH6clV?p_8PV@3fa0>d>al|
zY;3GP=P8-fr*Bl<**Q7;+qCdf>nRtP!yFtO4s5cvon=)YKW<yUetof{jg3w05nJYv
z$xW`Rs@uN5a88lFL$9r;w}YOZ!*%hA@$2#NaTYGF4LFgyg_rzGOHbhF)Vr?S7x$7c
zaT%f5uwlakwG<h}`^S$NEuB4kR_D3hJ{}&PHS5=}{+Med@iu5Tr>lN*jzL-|e=N?3
zutSgRz*tR<toxr~xjXcHPo6xf`0(LwRu=Do*ST}&;^X6Ie^>8)T3DEl$7pG5bC?}B
z9@vE^Exi1l$C=g4`DXm~!sO!~e**n?a5f>oA#tnrJoR;3nm=@BrvQ@f_0jJo2b`3v
z0_f6wif*p(|1B0=DS3H$Ezj-Q5OS~Hzo#}Z_-^vy>60fR%(svP86>=4PIVyp7kkbL
z85)x0kvQ4+LD;5Egr%>GYsL-#vGP!K?+N#aBeoqMk(5r|6%-auQBRW}?kqPNo&H|p
z8Xg%bJ=Rg0X;4BId989emn_yBwWDuoVdkaxQXC@rYqs8Pe}8|Gk&Gvk>B<QKK|$1#
zl9KsWpKjq4gvZ2eIC<d$2T}zmA79YiWZw=Nn#%F6*R9Viwu+03JDA(F=J`hP>E$66
zuiLUmwzJHuwcJMnIXxu!nDZd*k<0B5d{&m{22IYNKZ#hH9VzNeZ4PD<Ti4^nWfshQ
zA|Nl%q0A^#;?FaI8sAMjpSzA3h9;)u<nXUsw~oBWqq|vU6c!EfUDHF&`#Cukw!ZdR
zn%>FH&E52R?)utI<I~e=I00+ct!pava4lO|_V}7(aKJTtcJ>Ml4NZ)&#g@lf+1;;h
ztXGT^ksH0Xgh$V}?Yy5`HXndEMIbX|Wo1!$wPb5%(xj)S@87?l;{4^y4G4-fA=JlW
z=OKF6v5sCW(n;mp!!1uu)t8W<KeQJ+4tz{neeK${qoSfTd-lA;7kYD?mlxemojMhB
z+)c>3IY(Mr+83GU_tby}i^WtD4&F)S>aM#I%jdf)eUV{vE4H{@zIgHCaO<<%_-3uM
zlsv15NJL=Z=JxO3H+dTU8T-00Gv@YZn8DuOevi0k3{tE2=joe1!7*+7k)>}1F^L`S
z6iAkC{Q5O2UHOnrTZE|dpzPR}hiW&FRpiQ@I-c9#xO$bs@a2_#M|$O54Bg$`{f9jI
z8ki`YoSdjm$mr-WFfk=~Iu@rSC-=7(3x9cZcC|ygHnQEFPZ=to(v|M9<_>jrUAukz
zcDr>X&)K?}As55F;-2RhXMZ<MZ8kMEC6ynGJMcMk2bLw{!uvR0y+XyfQF9ZMN`%NU
z@5Sf(Ita}Rzuv_<G;iIqg+pBYKIQ6l6x(*}IDKOsHI<DDPVS`h{<tHy4fqAO$zRk)
zUek04NJO9vqkZUH%ZIWDnWh1r!4!yqzM4?Blgei}4j+yxU!K2%nycVkZr8QSXYu#?
zk#9wuf`Z!*9Xh0_q*UxO!YJl4e13jv0N{zSX26VxoBOHvlKY-Lds5f`1oA*2vwoRI
zj6Z+=e7rBwrzu%_6H5kLBR~*Mv&6oA*Em(~pEov^Jb97=kNCQ##?Q1mxbcDHYUblt
zDsavp>J{;4C?|A(d3=r}R8*B`<P2<O<_$VnD_V=tGJfN?y(uD-)EhcFb}#Y4!NJW;
zq7kSzOxD)c#iG*#pKhakrlhCeDlhjb8}M<96fn9k6U0d8rl{6Y=B0q7fB5j>&$&kB
z6{c9A`(uX`6cjF9x+FgTqEg~?pe*odgt5}S!%LUU3od?<zucHUEIEl)OdMehP}kDp
z5EIjz7h`9~vEm=cxtkbn6~2GM<CeewMm!2tki262(a;1j*F48QWz@6r-@lWLU*Br^
z_RSFi%KG6DYUMJL&xED5_2l4}11x>Zw!k|~OiZXf4G6{!8#i`g2VQzDXywGeOg#Jg
z7PTNYCf%YGnI+MCKC_~60|Qbt`Eev8x9LGTtfVPU5q>4=nZ<{RuGi~>_Z(ACZeU;Z
zN-PZv3!6F?7aN<DoXqNc(|cvf^@Z!0GNR<DefOG>$tSiZCfDQQ7|U0d#SnzRjOwF1
zZLuN*lL2_94vAcD*UovZks^ay`euUz^XCuo$JmNK>Nd`wZXk6t`=Neup8gWh*<C<B
z{iW%tsfQXF!6M!2s!RJUdSp3VIk!GQ3_DDJP&z#ECF%6~x4}#Yf`ZM>&1(%fXUZiK
zSrNWCl)@K3KRk6ebg85OOIKN08G|Z{a53wt33W(0Rq1ng7ik8#UVr}bWu-7LBGS?O
z@x1=l{UMW&kM}5U;=aW5743$sib{04!^wslR9ElayC?F&=vPLfcjfo*CprbjiwFAq
zYa%Vo%x)GJ7mHY&IC${MN5{$K?#HM}(XYo}Z<RnntpOl=s9V6pr<?y{D7X9<va>@U
z-INaXo}=4bU0s3B>#;0X<|f#^fPC}$nM9p_JkBla22>~T>EWYCz!!34eZ3ct((!2i
zz)40Zr+pNnQg8YoKGUZip;vTSuKFT=s=UW_q%E?i$4uYA07)@Q#JnHLP%%-QX|}U_
zxza_cuBIkrc@B@kpSOG_cux|rNYg_#WPI93K7c<6IL$|z8?ln2uA}dsnpVdgG+sq^
za&&a`bB@716kiq#!J^@g`ayx+O11c$WuE-yVzGm6v2k&$j<Fd5_U=D=GzKuOF<b9Q
zu^Ot^d{=MpS+fP&?R)p$y?>t>1;dv)e4&%CM(2rPw(cQpq%^W|8K0}~%9elKSx?W>
zTGc;8bA22hE!?%!qAtUJB%l^2Hlbr_8bTdSMfuds(hl9hsXPvZGSK|9$hI@jW9D+%
z(w}dhjyb3aK&+giqKurJ88lzYPx(@bAQ)<-tEyT{J&uq%jqJI+w2+dWO<fVets$$d
z%>QQ*<^S20-zMJ6a~8_?kIMm5rWt+OG%?+5M4&3lp$rbN<)?INz{V8p)*cD(J#=(*
zgUz`savD0cjW69CFMiFc6)0b1Ez%ZcV_S`de028l+ibleSvfi5+3~KX1-!z|+qWGj
zdgSV&1ylfI5MZ1*k3XyLPND`4NWL_w3ZS^u@iLZ*j;H7GjjS8VeyHp9UY+>`1%g6C
zCP0zzVgyeQULmc6#fST9MVAfkOZYUPsk#O1HdW^9yB4SR7i!({E8|yza@9&)Y&<<Z
zk2?O^oSB))tNr9;&hi1RtOt@e*3AuSh9zW?LyY6e)_lvMw~ip;ix+u9o?SUU!_`uq
zbGv2)X<^SXht!%zzsj2Q2m`b@;Y0ftz21E0AWe31QqrqZkC`6B`V(u{EYDbv^gXAq
zSrH<u=~>d-bE3Mo*1x~sve>{1``nKjgnEpJxQcd9zJ!wLsNGeP!)<L<7XFO%E+08x
zLBS|u`CvSGsGYnP$`Vz=Otv3dLbazR(#X5)&a8%Ip0zkMw2ZZC=gw8XeS7Qq^P@m1
zx;^<EB$XjW9d(=7k5aSV!8>93=Us_ZgKVnFVsQ@uZ4Tx58bmhE#qFtifN;Rb^R0R2
z&r3>>;@|phXX_cf9~vrYW|peY*^gp|#=J30M>vyh`u&kkien|J1(#aY=Q~k=w4YrF
zn!4j-FYY;e5)ERRl@j8y2e36u=b4QA2#TQR!bs8c7cYctJB|wp3p0qhWKEUD#xjuN
zyfi<JW+enCyfM#Q0V(MBpFinX{wB?%r%#_o%T<e``q-z~p;x=$;#vQ%yGGgy?x1Sa
z^S$%=-MtoAD|A9@YI?diC)|VjUA4TD61%YQ4pY;gG>Hcm#!gBmaCMdcD?S^-_zhk>
zK~epRo;4|H-})_kYNAi_Eu=XC20D$l>m+@@PsMug5e+@P44$g7sfhp_0EL~$dM|dr
z@z*c+PC$1nh!)RE4FtrIw1i+_Ne-nMg10kq6q8<E@S2}`)!ZDNn!11Bm1yq0BeoOO
zdwpbmBoKkryAO|dSKYZgUvM@Z?H@WuYOoS7oCYe5e3qnTWjAbPKF;Ov=<May>$jMV
z|9E9-WkpxKDJ-zK_!y2yH*!oEeMpgYb1)9R9k5&R+V5^&IUktMe|#XBnx0M;7aQK+
zn6h3*MrNwN@kY?@BdZQtHSI6n9>t*)r;6ye+E3w7xcKGEmtORx4q|cxLqmX0dqI2D
zBS@?olh>lnc#YN^(2Q&Gs{8M5X@nTJv!WT86gzu+<GG1m{g+olk<HMsP~Y0Rw*j#0
zYW&)z;+-_-vb5D0Yj+*Laxg?#XdFRehsNWQjZIpEF7gD!p^LQEU$eT<Oc6*6-1s$1
z=SEnVdZ>o)1S7sFv9c)q^KFnRsuC%<KYpAi(VZ$6PRpNh5bahk*6wqbj)ra`rECgQ
zm6wXcN=am7WEJoNfz`mS?1s5)i_iYCSs`eqZ=Jczyd4by`d1R%wPEZI3!O-igk#al
z(XU1HZ=j-@?;mn=b9-vp$O_bV<JPTpSpGLHE!uIyhTG7L;VDn+>+d1x?9XuPOSj2e
zx&;>n(Si|da{Kmr5KjQ>{x}9EwzhWz0_3mtwzjo(_w}8Tl9Ebd@&}>?m2frQs25Pr
z3T(^1ef#E^4=N-Zm3yaVWK7~v<~a{(AuC_QMsL}&<z0eUbbfxm$=*ucqRUEY@{v!T
zK1~9ysWJp&d(l5Q=rA*CU^Oob_-obvT#$i*LAtQd(fd!xv)x)icrAJ6o6u|Zp}c;6
zsJ0qy-{;StH*DU#AIJ&>g)GwnM@L5xG#tIhY6c_GJKKtwql#u3mEZUC+kjkk2GALQ
z(s=N5rmy$j2~p44gDAyZ;~l}f1h1pBc;+^F;pNMhR~Bal5yffPna|mJ(FkrkK=mkI
z9oD5vTl6HroIPdMh^js`F>}mucr<xbjg}YA2f!4bR8Y7>I(V;nCy_&k=pIS*9IvrO
zZx(sroDjPDj&dIrbjI3wW^$q5b{-f+?3>_300FAym`?n7wfd@wSXG`fUC-izL8-el
zKxT}PdBCYotFF$JseLm60wf=Et!=n}LIKPgve9DE<B1|MkP0p?F2ijFkEP1heKrzi
zOH-3p*rH+a(x*qua;~H8`*?XtS4{t0`Si9jr@#CX%LbzdIL<g)e*XRha?a5_TPwM3
z`LdDWj3Ht8)-X$WzuPLYcoI9J1E#9nfJt&&9g83<$f>`i>?wc$?f-vi*lSML$M=HH
ze1p}Kla&ow6*$3o_|h&>QPC@IZc8@PegOfM@81V0MDu$&kvz&GR&r^$??G0UCP$mD
zR@=tp?6k8wR@ORJoPLGNOwFq5>gxU4fE70dLJ|`bD>JiJI8X!d_6v8_tW>rBm)}`j
zuz6os_p3JioX^l{?_!5K%^dw}79R|MFMIvzbYZd?p`z+k`TJ?A2+-vb9<H9oPv^2)
zoW?tIZjpChv~hZ5EodxTEp$kTl}(i9`h%;{0!DckzwmVb{OJaahx7?XIFg=E*A87R
zs`7L6MMx8`o0`Iq-8G6q%k%Q_JuNEg16zaORZEknL#IhO{^t(|5CyuqC;=m7#A>QF
zGfL;jkE%jKLYCiO9Aai>-nDBN#e~K^&|IKa&bL3eU$bV79ZpT0h}Cr**|%@sQjipL
z$olKH-Mj0-d3^lz$#kNpHYPS!t{HfHZ&_Ix$@a+ZCKoTx*UpSAE%4@adN0=Y{@v2?
zPBwbIP1jd}fT#njsRN!<P*4!ZV5fzJ1%j>~oDca(04J2dTR<T~NEo0`QYV|iUx2ef
zN_tySaTRa615{H{(Gg$)@C7^e?BR8NkGw4erqg@z_Zc3|hZPUiQfl74<9*_d)*kfo
zDqCCI<dl@T`Jr5UXJ_fCBLlyFy+t3W^VDQ5IAoIek=Pu@e@Id&CyKvE0)0|gNLo-N
z?d`O*Q#0*~e<cC=wIo8Tp1V);0N!)#-!C=4*5}prwFFP%G(X7ACA<OU$1h*Z5!i%B
z>Z#fO?)`g8<kAN?^%O0wt)U?y73h2|zdWL&03V@W=BYFK!m+O*4Jd_z*Qjg{at)X@
z5VopiqGcX4TU1n3;ttzTRRCTPNR7spQ&>10s0Fy8r$a?fZr}d>Yk*up;#mP-;^eM*
zfFp<UM#IQBf6O-R?}1A5>zCbdN>E)xgAzMlFx7U>$jkTMz1?U(L1?OtURk|*HPTA4
z(?Hng(1%9lWmC(|Mn2RhOWmhan~@H$%#J7NAIr0nqo6yWl?wQ$Za|g%`0;_IXX)u2
zA)j77zw(=v0;$-cy4+(XIDqbeyv@6BTfkxe!{uv|R7qy2;yRZz?xSR;ahuBB;OyCg
z8lix1x_o0fiaI(v5dubKAAfFg9|L4nXDR}7=u1V{({WBqD{3$-fv<eE)ablVmP4<m
z<pYhm@cQjYBR5xg5(afwT<De${r&WirKZIAc*WaWm?*BSET14uCITQ*W|tYx@|EA+
zzU>=cRUh?Pe(6+-I%mH$?;M|ypr9X&-hu+_nxXUTLemgPFRlXzgw5+{H*eky;Hy|R
z<ilgb=UkR(GWjo<D}8jdv|M7pJ>5tOXTX;y#;4Id=p8?Cf=B^}E`A1c=?BEIZTt3X
zH*Ty35~+Ok>e~9P%ui4;0bMzqSBZZ`S=0t;iPKnFUw;P$(%4jE;<m$y6DJ6~S)7|B
z{3!UG#l^`Fq|&4*M6dcWJp2yOTf6WQ1ClZcerD!nx#?)P-`&ocD|a8~<zdS&rj=!z
zrzNno>FP#C7Dh$7RAv+%5?eT(^lX#7uCi5m^V;oDxKt}<I(<HXmyZ=Pr~1dthJZ50
zE4Mr`UJZzU9t=I;RAYhlIq<@2$(fR%Y~~DiOL!l@eEITm_bES6L(hy~ud|wO+Uv9U
z3MZD9zq7h}{ocKMiPQv;lzA?f8O&!A$~J`v$SdFzC>a~KZat%-au)|K&!mdVH&<;J
zHFbds|4#+A|23t0dg`tCvlKTe4!rK`zqRocL*K7oGH5l8jg9v@FQYeBRZ|P4m)lv5
z1c;L=Xw{T@_eF<<^qQuPs3I$8^H_?j?;0&<%QYt6;ccBC%du6?D=^u(-9+ltHt`!O
zBX@nc<-V}9uNoi~DQSuZ1>|JIpA6Htfk`&s3iB-+S3%!8e7T*=RS_i--1^&(A43`v
z#D4z#d0I=0J|`zf>dYC(#aVk`=}o*6z|f%W(Q?YxNAV4OD?%?fac627i479PS{5Fj
z0Duv>l_F5gQ)8WpIPY}Yf9j(J7=+9=00Va+A+2Rj$<4i+n=4@O!s*q!cYz>}OwpTz
zA_rK)U*85Y<j+{=2ehArtOf}fxaXKqXJP)os>y<?LCD;Oh6eQF{s1S)B>f$wVtAmR
zA0$@R{CF2DOxQA%0%UsamsbR#e`V<vZNY=PPxW654c(5`o_m~;z|N*Lg*9u}J_TP(
zI(p<Rw3`Csv)y5j9Gkre#{&`wH3YroCYwH>oZr*aRh^xQ>!=wi_C`PF`<wPDOfH7A
zgg~-DO}2M(ig2LkP`Ur^7WMAuP6IR`w%B=jH=}2{@Zmmn&!vqec3r2K#XbFyQb3!6
zzEB6fuqxMn@|O~_`bo$Hnc7cTHPRKy{#aVky_|7UlluaGZv77w$H3i3f=R_h7CcoS
z24OJ`q^m=&mtuF}-xT;)etnRg9fUIp!j*t>G#daZt5|&V=^_?^yR*j+l`V{lffQ0e
z5+OO7C^*O=()>C6yqUTeCV#zuiJZJ+N4SaDc9z5(gOAn$9G5r!UH+@cup~WOkVeGX
z8XM=2hK*0J@J)NWzG(VGCu?a4W%m6a_o3gcL;M3A?PFmfO%83`5jAb~0>y9+CDJm0
zR=m_%mH@V9r_TCA1&ew=@e(d_erDDP)UNVJyqxMj{K$9_Zg`L5ZWA{_hI22F4XapT
zZg+NemQz-a60^m_zNxC(&cL8E{JIE1g(9x4qhoAtP7*(%Tg1heQ*I3L^72|X=P<F!
z1fEB)g03zW*~m*%$7g5gC9;c)(UD)I20utU?Y}9M3(m#t!i9;+4-%%AF1^Fjr@iSz
zf3WJ{#m`*pHt(uHdV5k(&`Ua5y`o@L`qd9|avIRBRe{L>qk6f_y8VUo9W)ETF;b{5
zM}aVbB45?i^rsA!`mA^d@0C!tvpe|v_iqI2Z6u{rckc!U?iUrEPkF{K9wn>AccM;S
zOftV9pXY!L-+_^vVFd*bXovFRWS5E|u&e%Z9_vT|A^M}Y7mbs^$HqoubbH|aL*nD#
zh3q?R*_O`@^1cc!Clb=5bGZ$OO@<?v_fUYAF-KoJHTdO@k@uW0I;<K4)8)lEFy4VE
z4ZnM8cYs!pIp)YwSXh{-?}P4yo?qWDJbVXa!Oe^!{o(bC@ltsg2Q>aCG|BZ<E7W9Z
z&L6usdkUJL!@?gM-!r@9-52{<!m@#jZ?0Sy;H!GU!rH2fyabu`>4o=<O-)UzASl|~
z_Z&HL1m$a&xaZN08#kf}U4IqWy0{sK=+?Dsl#t%`@7qVo$H#YT3sW8R)7xQTH0ZDb
z(RzUAfJSmXICzVg>u3*>27qvAObmc975ZJU3-WH8@%wK+eG11%f@ZLS#EHb6VNl{i
z5ijPt1<m&I;-m_Ma41L{k@vym?Y<fq7|2?`GTybCl9Cb~+c;QfB#&1(O!A%(qdcnf
z%<KJvgMWbmiHVEL!=Zkpl}&Y0QE~IDSFhS%x`oR}@-#xsK`fp9QE4mvFRmrIN~Ks5
z#--h+`nLnbm{nY*9R6Oi)5ph0IsWJ?R4O`tQ&N*IUZkO;t3o=`E^*1$@7F~p##uE1
z1H`M7cN5%$@THc66hK28H*HD*D?%_=Xeea`w4^H#AG*4_hC52{VfBQ(7q5WClm@_v
zh+_h(MPL5hv2P0qONy87(~nvvZd|`ksv$}n2eLOnO&(GKO=mgUAM(-=2kYjihvo=L
z<PjYfRvCZHF-F9S2BAyTRWwa^aJD06MgOLU2yfJ#*<>>_v++M8dKa5>g0L@WPM~as
zp(n?()A6JLxPjjyqOKE8v4R2{=#;Ut1!d8<t*ttY)P8}1JpjO0JUkS>rSao+v28BH
zEw6xBpSw+hu@Ff@jd_@viMN!*RzQ;`?7?yG#TfATDJdzZkwbM#-3uZ<JOTg5TAz5-
zo)zVkXyjN5${#4Oh&BH)BlMlx`Ig)3>gvFLZrHthxA(%x5en$ZYU=8z&YZd3R$#3G
zb_BHC$B!Smemj#AD#^73Ks1|7YCS$p&}CQ~6s8OyJv7e;IQ#LU&hkk@@P-H!89YX<
zK{(*i%DIo`DX*!(bGpq>aU-)w9_T|lPfbgsJZRr7MOa=>&*Mm5=rtN2pA#sXA3Q+*
z4?eFdS^5r`jH)+p)&Mpm2$NLj?(UWNg;1YU&%|HkGcZz{9{h4zXU=DJsIIOqY8K;F
zP|U_=W^XF4t;PY_f(-wrt}X!SD59V7-%b&igr_~>J8o{=aTMKr`O=@=&n~>LY-x#s
zaM&ky7{H*@+U<0U*}xab&P~>kv?ALVu-p4tSXhj7K!#H|4SfxI^G1qh$BsEjGqYW{
z_m0oZSYR>WR1gHLgidu7_6mH#v@uy4j(}@1F)=3f(a!D@qj$yy_qi2+i)jW*mxf5R
zQ@{`$4;z@&o2VO2MYcv(V)}nuk~Itf*kxSUO!E)-Pk@R1^iYirdbVFskU4l5wEx?$
z;<sh10m4ogF}U66MTeu5AnN?FiRWln9w;D$=_YtqP{yytOV`5$@W5kc)CpPuhy@dC
z>pN(@&?Jyz4;GvBNU)Q%ymS-BG1<%@baUV7TXut=x$!pOsksY15h@@itFW^DAPqEg
zL98fHx+lJdoCK!)0!Tp->#u>pI>e%J{``+KuKT6(3Q(ZOjabyPR+!1stBHt+5Z2?-
zqenQszkj{o{b%&M0(6Xn2M?Y!Fi3dtfQ9stX!^*qPDI*+5{Fx5;8Vs{BGLfuz==WU
z{$AW`ej6?A8+605hpg!t85v1UBBmICdqSbZ8AN`5w7pm}TQ?HlASxKL8&o7vD#JvP
zCTIy%Ji14ao5^7Cz`Q=GnV=*v0lltFicHY#uY0yF1=c%>h}hCH`|P_O;lOeX?tmE6
z($XSaJFug-y5)V@LVBE&<pWXy(|w$xG?hE0&z;*TAt3=XKr3DshYcaH4Px_=PS4jc
zF&%TC;`;ja>%)f+pTKy*p%}w*?p9<Zot2f<6qH4r=%46gQPQYN(MfXP%%gvd4`n-p
zd?JnF-wNl!ix)2_W@l%gI1Q+yCRbxOtl)YAzW;I0wv3Vmf(zMZ3yU*Iqo~loZtwLz
zdHVEfSjcehs*r0o@pU#fh7J#30ws54{0AjM$K*%FHT@D7r7n-?goO9t?^DZ{78glO
zpf_Ao@%eKEShFYgKV`sCsA_1uMh%0>0!V*bXqK*fM5N1gOKYpMK>KZNI;yM%fdK(R
zbO*fOKeLE6Gp9?)Mi@v)Y?tMXV1)aG*Wg72PV-NYgHBE&;GaXpE+8lO_xGc|PYZkz
zDsP`&7Lz`6=I7vG9eN}RqK4UaybMj(AWcA}kD8kQ=M_!aZ$8&Hr0!VLWfVSh<Obvs
z)udCt<<oJb<gSsNrOlJN2;Yui-1y%8qBN&sNhe?FyQvsWEdrzm0zRoN!0HIv3X}t)
zr9%lqqU{xvIB|jr=>Wm-mf%{XVdzwloMne-A*B&b6kdrR#1#Nm#dGGn>z?CRLV(=u
z=O)Yvs>QL5J!})#?wn&-8bFLL9}+W=#9?jGX=6T|`*PqL0{6J*YzX!M#g%j9R9b54
zO&pDgRKDE_jm^!Rs1cBW>Vw+aOFg2ooesk-f*^wZpFR~NNvopbN6J{qzu3Fkq_AIa
zlld+9&pJ9f@Lub2^a<QWhJ`7FtTv1zI{+EY81RCDOkz>cUx0*eK6@ryboqN&2drz=
z*kQDMp~&%1Z9BygSGOS?q1Ie+cSnUZOjk+dKR1ddkTgMrwrOjN11Pr#lsYvOD(3a=
z+qZk@H7Q^xsUajF&>qf-=j`~kz239e;1H0LYeO4STXc0EMS&z4P~QkYKR>^dN=iY<
zB!EyOG~X@$X2802$bfZ$@En{+tAz7N@F!BiyL(6Oq9UHRu~CB20W!Bks5wq^9G*Jq
z@#A__4sy&vQipUjH#M1n`6Z$Xpf4C7DZJ_~bh=3Bq&9#U4hL<6rA?hgqI*(Qlz~F6
zm>?QS$X&b|>kz9#=Vh=jpnV7{#;gB)8yIuaH{qnZ&5Sa^l9Qp8tqb(B>e#?nm=dDV
zS{{yqMFm^Lh`;I!EO+2sjuc)HEkne(^53RHmEJE?=~S#*xwqFqA`B7MESv*6GWZ!_
zZh9RVEJK=)*4eXZ=qW+?&|jgx`uVdaOitW0x*&s7XBdxM-W+1P`y6^KD0MTeLt$cG
zC0GH{fTDK;9aM~fh1urht0YgiwDj~Q_#cXWo6&y3-zlHt^|v5y5F*V6!&-L90|%ln
zsq))0fUj{d??G|>m~NSOXmfFWogUm&S)M8D+<KKe%N%;Czy-l`wg;;~xDlRnIfS_g
zuu|)qj`%WdN|O)VO8~>09k4i@L?Xsn|I07}xu3VNIM@FhUx*j?f(pwyP=H>4l`O+{
zik<xWAqv?@>rVdk$DkH~N~J5N5N~C@sKY5KCzn~{{`SqA@$s(Hk2Et^RREBJ>^Tlt
zfA%@E8^Pb`o;3WV23HOfB9=zG)cp|Q<ADbV2#bx?F*`%zKrvRx7Y7tIikR>k5Gnml
zX?OI`m>`Z|>)DFMgquQENy!}SD^>GjWXkpu*Si4jjnC~(`SqVyKzE@`9nd8(AYQ`9
zFixHQQ;DlBM6?gU@1zzX04$)&0cHlE%R8Wd_vL>S!AvREX`kqR*~Qm{B1h(<yYDdJ
z3Id@QbjwX&UrIalk6@aLeOAN~IVKQ>6Fq}oj(8%^fXakf$=jiIB^_1y$)#2yRJI$C
z?SSw!a}7&B{>;wK)+xA12i#7Yewgswrw6N09(#icuY(^WN(#>N4jciPJ?L_p(Hj+m
z?nKV}1z|$O^5az;t)D|f3fM9@OR(H)upGl9BhVnD#EhakMtXbMgYNIzz5AKXx5I;9
zvmeh=^PIGj)8do2QV8W!{L8LKX_=>G@BP-0Oq05z#2PwZj-<4LGSLo(A)2{+h1yMw
z26EzQJ-yvvKY7kRx_Rr?TTUZ3Td}33CI5hcx@eK5w2)p|e7TPAIjN~Po01={8Cc;7
zy+j(Vp_L~qCgme|QexbJFy~n)G+8+5n7;t_2CumD%$YOjdgWiL&X-qobTH#Tv$C`A
z7$_Pr{_RC>3fzzlp%=f^FYCFcb#WTdJRCH45aS^`C#N^9tqfOz>rk`NWl2JmA=DEL
zvB!@eN7J*;fxgJ_g_B&I@CsDSkc0$~95!%|6y`rDVj&0tWFKTZ4S7BnN5>Q>>=bAS
zP|BpiFab$|Am|z#<S8<E7&t77F4Y`CqK}VD^4P|}AO|D}yWL40omhli7qB{z4hZc?
z>%KSsJATj1L@z5t_gIEVBLs3C!9@jIEm~ArJUZ3O3(y@%H~cn`0onwEhld9eFjtXz
z<}f2zx_$io!FW*(2<6z#*rWEzPKx$cpWNynqEwd6FM>OVoDJ729dtKI6fM{nJwut+
zfa0YWFnkB@fkDJ_+n+ywK0i9EFuDsw6+Y$|q;#y3W~RC{Rrut8l_B`~0+kgM$ZFth
zt0$dWOC00ilaWAIJBZ#vaoPjRFIZZl+#|EV4@xXBQB8TPSFM7e@e7R?&eH8zVT(Gx
zRRY}qsEQ3~&CxUAqvgEd;-D)aa?qcy0ZHNnP5^AsZ`i;bAfCwFWe!4hM9G5rI|e)%
z@;E$j>rc2(Rlo<vb|#pD=xlh?S18=FW@h_=%^bGAbORI=gh{@w&;~XwUTkeQBC6@e
zFPQyyL2IG_2E!p$gA_A7JY0kSo$CM|d#Lk_aB}Ji0nbn`u^}}OC}syT5?k`Eb^xpx
zH^d*Km}?st9u7pAg~md_e$x#{h^Q*}kMBEvJRVF1$t!?-n@V$Dybwi}+%G5?3OxGM
z;sY}z2E1bzv<HW3evlQ2Nb+S60s)DMdpVWkLk4qY+nh#)md93>x6XDR&W3z(0cs`C
z_4b`RtHCzU;b~$HS!;#PG*ngjBEI$Y^@%GBg_)Shpv%-Up(u(%H*A3o1`vms*DESc
z5=IwN>9J$6ct)0tpZ!06oW$8}Eq3IDKto*UNN|7MWfr2}P|gvioZ{llAT^+0z#?Aa
z^d6Qce9CV)ei4Hx*+06wD}lA{Tnhio+nI;=%SNdF^Qc<DYXUu&R4J>jVc<PDgkOV|
z1yD_S{8#}8j5vYMKGKxb(AWWf24;vfqW~<ie_`QaG}|zc#bB1=J|09tXSG`?9uFm0
z1A-`+9ZN{f*hsQ46vVTMrmAaXBnX8WjkPhfa7#<e8uo+r#GnoD4vZIRqI4NBF#sH{
z(bLl-9|1KDVtB;$`ia745HKD-ehlj+tAUD3JMd&9ego7>OG}F#Y>Otjxk*VxAV8%i
zwh4$pf|egyE_askF?~Xd2R;%lEI*b$4Za@r)_`=Soo8jvpJxI04-X$141mR8d}^u(
zQO$AUL}|@D=uc)m2q7k5Pa$w!Sy>rYBYja~Q7-dZP{%JJG6_gVF-t-9L&tF*o}Dy1
zTiEfz-U(SW>;d;cj15?eUtsWv0zpAs?^tdVOG{aF0R8B+U?Q#GdH9I)pr)u(|4B4w
z1TX>WZUc=@_Kj9n(S~OqY77vQ-<>-@Q4<|DR$?*%K&9!a>6v0j<lIeswis_AYzZbU
zB9RWs907`wZ(g1d!Uw{Kp=cpUmnPYY|FzYp{I85bNdt<#tb)P<@5}=*2;dH$x{T-o
zQIjSST(f#oLSiMU-Du4QY=L=!q}NwKgF!GCO?AWwn(iVFn;FpT#F^6i)O0;k+-s07
zalckiFi^YIYl+yrcqoKnl$v74zLsLgjH$9qOtQMVj5v8~y<LRx<}3ho$Rz;pRdCw%
z7Mh*i@4J8nR5#!^DhmV&rSIkF^9#Ue57bw{Y632RDN*z?aF8APdY1JH`whQd_zP=q
zwo9E!zB$@i{sEr_1Mu6XCK`D3i5niK2UR<F2emy+OambI!G3kak~BL%PlJ{kEE|%r
z`g+Rcne#{f(G01MAUEEiIU$6zm>A){@RK29x_Nu9sT9EahCXHBd&v=-w)|He9ruAC
zi`Sb=(-uUXuZ!S@z@R>_r*MEX<QISfnb`o@JT*17>x8=qTEB*9E(6upy!BqvpVIH}
zu;J73DvdC-dRCKTa{Bb^RT3pAc;VQUr}$HZZ$-zt>)?3`OpiF2(@ve>;Z@}q6Wfha
z_3J}o;@Ao7PTsR;48j*SBb?JQRfF^L5&k$>ZtjiECbumLf+s|47cIG_eB<8JPW$C$
z59dmViyO`#GAKMbhc+G=A}l_h*R=sX2u4ZRgoM;bje%rtXBm`40oHvg_wkvZ8B>vw
zSqBXB3$s)B6RMf&?8SK`Wbj+C09w?9>?6Ggbeb;YGz>$KEC90)FueSokWTQNFw78j
z<?!J|<}LIf8o((1o|=j<R6rFTy#}LB+3k*G^~g;~5p>1d*Ik89{<Ej&W<kLrxKqJk
z{z@6lwQO@z!*V`%8HsDJkyKZw!MBLT4J1nM!Y~CM^Dg!q>N?o3$k{Slt!S*e`eQA=
zOtx_l(n!<01WndpEs22~T-JF@%MCrAoR>RZ&ebw(uiF0iG#YK$zQ_>~LGmb$EoO;G
z%6JPl3r9Q;r-Ox4@(O@28Ja@%Id5%Uk7J`<bUA@`BK^P6_h%o|L&faD`oKoGnwpv#
zB9iLA?qjWCIk;AmH3<XjK4lpZ8R;J!ECYN5o~{uR>GkW^iEkdD^%Mp~NCOP76NY&v
zbVem1^Bnb>7XiFKsi6^$1iFoxng9C@nE2&$67ZwaAbm1a5*>hs?si-#1b<ALXpoEE
z>PvJ=_xK6#P3DGBTr!ZgfyN<dZABi}=+O-a{`dN7<Fe19tqB-97W6&3<@FBq0Y)#J
z{84VkN56}K;jUJZSh|TSK`QRSgCQ^hD`YnNWHd1^u3_zYBtm1ummq#dZ{=~4O>yQ!
zE{&(%&Br~W<g}u?KLtyV-&0jjW>Y%_w__jjJZSdci*t@VT3IzH<nW@fpga;tj+_LZ
zYU7qI>Bw<}bcH#N^4O*;Gb7*50HDwIMjLI|vgHCig-4Ga!=#TKlJrI@s<3-o6ZMd!
zKO{=@0Rj+48w?Mo=jK3vr49)Hcg#;p<<{D&STR?A5J9H>ACn-jGehHt1EhgSdCJOQ
zt;%YfiT5)KVe=85woH(_WLyEPJIb?fQ6`^XvehSPl4Br>6A>Eqo}lrxG<Hznyb~`!
zeD|jyHhDZimVR*<UhzS4@+rWg4b;?;GHLKUVUEreD3#;_coaZPE{9${3Bk8}D-U~}
zyk7l3C1*aO&|5CaMn|VLO*~a;))f$5W!yGZlarlY5TlL|F_xolH?6!tY)xWeeO+T{
zmJL`#l!5!D=-d7nsi@IgeMk$JE#x<s+B=+>k)9r9YwT=j<nBI&%qV!|2!cm^?Yb^6
zxxc9cEvKQm_!-tiht5)6u|}l>%DL43T+Lkqm<n*k6jcsT0zCe{0|yl3ZN)L=5V6Gz
zegT=_J%m<)dV;)|*TQ`iZZL?Xf(ZD{)YMP&^UdI~#Z=2)`2XQWdynl;%NCy`J|tjl
zV^n>0Ca4Ml!#$X$!q7nESOFRYu+dW3CMzgYuzH^~GTICN4YgPXTbx$FT=jc$GCbX_
z03JZwvblBG8#3_Ws$^t@2p+f&krC_C2eLBDu#^#06sZx}*?f5XrelD((&^r>SDI4z
zczH1Z&;`5NTreIKg4j*4zvNGYMSuxQ5EMmp@G&@jkwL4G8*o?%zlg)4p!pWP6!hCv
z00wPs?H>aJ+^$=x$RO0J)vE_UhCyiKxBJ%7U1sg;^)|10adFYk!J)FVb1(XT5UMfo
zGN6i^BW>(rWNd=Jdkgb%Z8L*^BtS`>)0ys0<;*B<xd3}f80~I>&BTK%-a8xw4==r&
zr!ffOR2z%4nwpkPsT+xU2MP%%;S<UNB09&;t+uw7u;WNuc{pTHjP|YVt0mK$SR}M+
zRv#ZwqPyYb;JAhIO|yHq0uni~KH!+2n|%?GekK>jTlo!%@cAQ{A)8X#jkX^{rMv}m
z2yrqZZ^obS(9(5HmSq56LgY2@2HPPUK^G!UEC76Imnj5D?X}hGiA94<M&YG#k_k&T
z(6)EMpq|XpfjT7=&p`mKLfg&;6paBGQ1QMfTbTXjk?Hs+rl`i=Z`-es=>pk2Jp^=M
zEZ8W!fhP7Xd&POvG*35teSj{Y2UX2CUGrXC94P7=j~?-0_~Zm?COaysd2i*yr94_w
z3NbM;9HCTN)06yF&sp#>W-u*radU$Q!|X02Dh}Z#+1m^?(OROh(m*MUh=?FVc1YeQ
zmE)#KenqXI<%i$MAF8i{Iic5}Oa<es@~<o)h~{5vrK#EIfZE4$@ZdHab_(QHDU?m%
zILHZSyR7S*QUC|R#0dfFR>9i+<jFy9&jt*aG8z-43;qF&PaI%s9>`;uD$=sn8W<RW
zHuFU|gAojMI32*lhQNgqAus7p%_wpn3=GjK5Tu{*d#8qSk$<qY18oHd1_lNQYYT5;
zH~MQh&&B6UqVzBxcmMu<Ao-7|NoYIJD2JBaIelw$7yM4WAY8zd7<73E5c|TZR@HPd
znib!Oi(ER0Od?!08y^%BVg+rEwn3rfPlP6bZ|W8b7W2b^wZ9ZjFGmPD6d4>ogaf3V
z6OUMif$x!L?@nixq}i$d?xx&H?>}gsfFT^Pm6>d6`t#EW+6i{$)5;m#Y;33br5bSd
zut%~!<uKeOde0Ld2L^iwzC7O9={ZTQI_0XQh7KpxW&V16w*RE}nA!ASPo-qdV@22f
z%bU2r_!?yFXWQuZAv#Uu@xzB)PTr%(mW1-2oM32;V3e-c%n$6QS3cd4{O9_pn(>S#
z{BL3DM)igtzUSciApY<L$@ZkfCjn~&?Y8wRs0NqYSy)-G<D-b~hW-IrJ-q${*I<d3
zYQrtoL_yW$U_aKs3|5-ItPlMfH}e;4zil%#efZsmuFOwap%UMS(t5S>O5^O=NWF0n
zn3g@O$vFVot+2Hdj&#ZgP}sqxrJC2!t0js$2f%nPo11vtP5ttI$#eiHA3gW{vNCaa
zV#7T6V9bT66~VPMkHYPc!Vg6Rny4^ZcK8)po0B3KfQiuV5g-LP-a914Jz=2HBfQM{
zm*0`!9lFfBVMPO*yEaV|$bHwWh593NsGEdN-?y(TrR~3!lrZ1$0YnGX%#-LN+#g_C
z>JVUkzRkBN$mq~mnmo(1%E9TO9VKI&WRMJS;OWz+lAxHn+#~ZhBc4gl&dA`DmzT%j
z7ZT1NcpOM)Pgi!C%!r@~MTez68~;)!aMyq9ACm#%r{zI&!hlZ&7svpwG3izy<D(FK
z0?&Ht!zOBKJ|Q+K1%<~gW4iW<ztQlMrVo#q3iPzr5QB7TNiOtfQhTGA|GLF^CfQSu
zM!%`%5bxt?N?hCJgQU#rDnI?tLLmuFNJ;6v&;GP|$ESIDtQZvq3#*F08LZtd7??KE
z^HQ9LE|hQGOk4vL^t{?caewmcSqh*IVN?-VwUIgiu5dF3q@=Kc?V3U{YWe)@rFeQE
z3d>ViT|uH<!8|08_AAWiV(Yj)zsJPvLfAc~`Ep1AR3j#D$zl;{0lEk|`{)#CkFq~x
zfqZoVq$RPBf&fX%$x+5S!A`?1)S3MJ!7IR1x&?y+qrzp-_zB1p7S>2A^rQ-n(wqOQ
zNex9ubnDZw{?^$hzBTkx!fmioVA+>VnjYOo83+yz{w!CcbeOfV+-HR*a^OD&DXvDh
z#FD`4QZh2#0|T{?3M5_xqNdx!<$=!EvgJvaMb>u-Q>gJMP;0Pb81!3KGv}H}xbxSL
zoZZ43kxasJ*1?OLyMbLzOFiT-ESeru{S}^#0;*H&zzzVz0ox~(m>>Q9eqf10gw0>W
zZH4(>IN$r5bN7Nrd;9wJ4fK^Peft&>ro@g5T>$Ouf8ilrLX#|kS;!0^L{psbhw5om
z#PNXh6CN6R4d4dUi-4VOEqrT`TYsRw04h94ORIt)d8fT$8l5wAo{5FA@|4WXTCDa2
zlOt4NFlg0awKG+dRw1O#(A7g7!&>=}>nmW4xEh~rKRrE-Q%(((yuJd=AD;cNP1{YJ
z>i>;@RERJq8XRfRp{)8W&vBAuk2C@U6XmglQ1~9mbQGi@Q1hE`l)z}l;!!c!xR$t8
zfKWkM{~d~18Y7Ftp~N%(;?}KOc$bgh^)WzdZ)f)aUT}vy6<}!oJJa*+{KubRzyrHw
zHZ%Ht5u;qNLij=dR}k~yR)33Tj=T&GH%P8k@NL4`76=U?bcPQ+035PpI0q4c>5?;L
zYQYe^Pz~Oqd3$JBDvD8mGGj}qnYjBFkRF{6qX)PRlNL^J2AE11XLuHM=w+bRkwP?Z
zc5u}|ok@*8$`>TAZaf7>!H9GO2S!hDD-77ksjoruAW0)7w3fIE0Pn0PZ@A}#yQb(e
z92Kbep%D@LOI@&Cq`HnMo;ZH|C}y~^esGbkff7xGsK<}3pU#}QfKhfhnDeZg`9Uv&
z4`xLOMs-Ml6U13%haU!9Nmxuw4bb8p>VN|Q@N=MmlMWC9!q3rBWt3qZm=18+Mp$r(
z#|%HLh6u79Oib@lY58`3Oqac4Xm1Xs-hQfIO)E=V5&|y>*z>R!N^{5$4Gz-m+9iwo
z8K7-vX+K>Bg9ng66&iMmqjo<i$h8zmc*Lj$4wx_>AY_5dK~hs5V>=GZ0>Kgl;X(k!
zx4=oVadF8$-Ks{4<xQc?&q1;g1tG=2Ah2k(BFX@R!++Jlda3zB{3I-wu*#TXkJRVL
z%vI&hjrzq7Ye8!RO%~&A5K*k4EAg%hO#UFB(3>727hu@g{rF~Eo(8)`ll%6XRz4t4
z$w0<K0SH%mQPvPW^alXaYtCbG2D=|WK5obDxXM9X0;~rVI#=RrKq3pE4$!!X8F`#c
zGO_30BH_^ECz4IZ>2Ua(aQgy_1?3;OQ=UTyLR)x_>v--%Avm}Q-NC^jGrEMsh0sWK
z*rb7!i#8iCu%iW00q_HKYyYEy5)^?P41Z9Kl0dwX8BOF>V(Ni4LSUpn4F~|Vg3|}{
zgdX7Fu(&vROUs9qGa7%_FE8!0^L`SLXiMR%ap(nmq{*MM@6e%0O!?F$a4K9;R#K|M
zd>vAj9X1#zPEJLo8n_)t!+vGi3mt$g+S}f*wE366>*gfjQ-I27V@y>w#T<n(n!K9<
z17ZRC%QuoG?ThQ{ZBXLykb3hA;JHETKY`K=;v`i$NO3gV(0uv|rWO1vC#en)rjg?4
z(W5m?E9mUegl`}kdz#w1t6-?PBepmch6nlig-j5e3<Y5_C6;H|V6y->ybIYDtYmN7
zeLcyUFBn<<kNbbPG&6@}BdS7<!I(9$R9VMmsZ=_=r`5hV;|NCj!Vs5Wy{M5*;php;
zcacngc<``vuZ;z)Wze)bDnzAkbej>s{xbL_QFQtycp}23fosFxgHa=;oy$*A?whvi
z6+>h5nmRB5cSPJd*h<zzm3J_9fT{ck_8xa}+y#+l55o=7mXYZ&m>)jH^y%x@3pj2_
zv$t?6$<zTjmRJ!h^=lfFRP$T7Ux-EiqtZ40y+<*uZWCyv2`@>^??^h)oA!TdZtjCz
z-6ZfeBwT`WWudAaoa4@&J3-~7W!=Q=ksYE2FA28vt%VI+PyQ!NXwNUerYSutrP=i0
zc{>{iVQq1MZ=j2Yh^U#oJ)(V@qU!Y|73)G4$V`EqO?^Lq-T=D`7ccigM>fpa0xl5e
zDE#OuIC7IrJJ3_Xr-D<0nX;JLa87Uydtd;nhsZVQe35$d=G2Olu_~<$3M4yLMk}Nq
z-E>_wUcEV#i_7dX2D2(8b_>m9Qf-P2hnFyvR;anm%fsqBQ900L8N+PlP(FMYN0M73
z{Rt!u*v9sa$b3mt*f~J?5+W{&&Ml-BY2B>v7!U`(fqZkpUp<?y0ApN;W+@o@!78ke
z<~J~bDB#Pya_o9H@iO3x3dcnwzx8eSfGOe>q+W8R2mB0485z~EU%x|Zl{R)s60AK;
zWp<%D3`G0ER%<>~y@t;I79f&+_nVDYx)G3gLOyML3?UC~C9I`>C<(@J=|FWwdm7Lg
za_TQ)$n&R#2_is!P?Tn^?>m%8zneF2s&5zK3>Py~MlT0WfJ`N0%0W#-!xWjMz06Bb
zv;%$&<nZnAvf$>Qk6*tMl9l*PMAI=ehsr|&2<!!QkJElIvAr_X;+#+mQLCkJ+R?ob
zLu`J&2!;iyjxRf|srr(oGx_ZElH<+3x!KttKYzZ)5(4&f!+B?l6~e7SxgQ<Pc2m-t
zBN?L7+$8KDjw_H025q8NQQpIp5m-)8t>&Oej*5w4swWU5K6qE+mV=QH^&!blk4ocf
z_%(&_ye8#sHj(VQcmBRT>#Bj}8v#_Y2b8F&-Yx9083P{yk{#ZaKaQHnR!Q%;v;DuC
zv%k#B%HJWSx3a}tJVcr69`gzJH;{t<dXsTz0=_5Dl-K>I7`#dU;S&4y+OOBgdqdfE
zL8?T)AeVO~LYntX{{L#xrBZkjMNNa8A!zbu12VfjCRWjv47V3QYq?G4&N10_8qOPX
z;R(C~PW>OR0Y74}TnSSS;H0v23j&a{U<Jl#)N7>9M4#nYPzU47OCB(J)MA-aeT${p
zO<%9b?DC%L-O24kZmR&*cOPi?H*BWZKE!+|ebD-~YmF@}{ZLW>k$-~mrXbY^Oe>)|
zz|+mb(an7>XAcJl2l38553)kd1nUP@_y+PIh7Rt+n}nZ#S7e^UTH79wU-VqadujR{
zsGjGrdmuqQ0P~9LxXNm_Tn83F-*5qE5wW`gv4bX<-BnR-M*7bjK$!fup<iC_G0O%^
z6Y{exGz;jf<mwF64k6c3eOzCrf`Uz0Dg3y!cV__WU#B#tH0CF~bC$OLKbVA59;_LH
zD6631f$1^gumn)EKon9fRhGd7M3xEf>jxVXASk&Q3gf25KVem~!`MH{4&Fl0tY#a;
z8D-qzg$iW~7LLf@Cx6$r6uY^*11_-Hl!`*~w<^(x4hVpI8mb&D)>3kE8(~<Wz?y(1
zNQQcitqzC03CaC5yvzPDW#R)-zt+3D&aC=2($n(>ts=Q)3&S-8B>+0(cA8*Zod*6f
zT+AEEf!w);FCTR3SH<T-la=ys)6-=5KP$M2iTHJV9z1Av$R-faV}Rb^GhNN~+l%`h
z@H;{Rw<S@*S_7M6J<=A#F^BzVWId<9oNKaRBh<(Bkmy~ZvuiLaOUC}-_Jw))1`Nwc
z?`G!a<jNc0Ixe19y6`2(V&a2KKNki#azl^RZDuAWCQ|K{lp@6%prBEuVF7mo8^RS8
zg0WOa^uQ!)zyqNZsp2s0>zK#~&*adIdQXLvMI_aiJ}b<?qgGOtIFcCOqaeI9=q>Qm
z<hBz0efVP(kzfdXL7xcf^F<Ad1Or3~U~YoKP?nyTlt5K_4L&ZF?=0Zm9neS=&{Nq#
zApsqK0)OfI4Qq*)0;g_lYrC~)4Gm_lCVW<Ad@yOOz;<>mw^7+~uv=u94~9KxP<P<>
z$IF1f^_lXj&Bn7fxs*d@MJKcl=2vckRG*b)qG+=7{0CHmL?teXeJ2bKQF8&ZA*XH!
zMTYbnB{1~hpftO7eMIUGN}{}w8}10D=)EM0wA_oOckr)aNqmYq3T3z>(r7Q&Y`o!t
z`#w}Xg$k2fHzJcq)>nS~{J94JVJ-7xbZT%H5c4(>jiByczRd4S0e$o?zOPVymqA$O
z^0n#zP3Vlp0?Ur|y-%ny*eOjGg?Nq;sfb_=cca5L7%&JzM4bw6qy+mciR=J8PewUV
z=|4TU|7kLICmH=2TaaCC;f?nRa!KjwTK)eKOPEVav;<S97<2F%aoGYO3tE5W4GaoO
zGs<(U$Jw8WW8L^wx_2$D83cY@bVu}W%(BK};1R>$u*lH5jU=ZlafbyaoEw$85F5tN
zd>=v%(!6@!ER<nl(+87Bcn0__<g4pMxrnnDXAU2hg7S+l3=*enS;TO%`eQm9TQzet
z3k!0~%c>%WY^`iYq?xrGDJye*i3FD6Cy6KE)@FvvtCXv;wwnEAw5boq3?;wydXH8O
z5b2@pIIExXwl&iJ!EZRp5DN^$ufBgzKp=PZ^hjZS(4B?RxBpU(F2e;1WkT{{=d=BY
z-w#&_BHKK9I%l-4g$&RbB}m+2t!;s$(_y3(g3uYGtqy}o?H4e+OJ>6eHwh&Rh&CiF
z>=Z7!>5<t*0hd4!0uitkCa5OBxw|h4Sx5NDC?kMi`0hD5`M;M<t=&YgN`|Py8^Lt{
z4<)fzA&GyqtR_8*Zsz*}r{76Y$yp(P7E#G<wEM7EZ~)&x6O#PsQ9wch69Fk;FW~*6
zfPe(o0~9F}Y&GnxH(=P@XT(s&uI;0kfbmgCT@QeFh*=zs4IC@uawTJ2VS&JP)~sx7
zR^JNwNHc}Hz|MRP#-dfIfxnQDNcWB$H$FdYO{_V9hd9<``Vf)4>O(Hl0(8ez6p_8(
zwGf=~gm{L-ynAd+1wgvkbqo{C%vht08r5RReRRd%$<G&vs|c11;!6fH`T-z`Bg$cP
zyC+dyYjvr73Q)wXP#e#tpao4Ho;uB}*+VeV!#d3uxnyKhgaJaPWH!l$+*vG~1#k<y
zs7fJAD<~JTGFe%H7>L3A0*Ku1k&*W}u($x=RYe5_@G^|r6g`VVUYHC-9=xOYgg+Ak
zJQ?0ZZ1zKFN2^0FbbzMv455LpP2!QhblB6K{~c!**)Iw`A199}bmSfxxMkrJebdko
zjKV@RCRk`$lvam9(@90wiJKL;J89F)AD34Bcfws-1iwK{vgr1ZPoZ4>WkklsEFi=I
zZQNE!qywZnu#$VBF<~RJ?Y?*UXyjugFUGbfW50-q_|oL8dc?n}QlFCSL@^Qm0|!bz
zuXo>geViC9D==R_HRXg0la`-a*9ox`>nBpZxL)zvH0kKIpaQyaKT$G_F)J=-mk+r)
z%8P#imB9c~k28`JgP2`o`>-E-HWslmJfGq|FtVocYxxbxdixrq=O=op<Lj+S{Vem^
zy?*_Ah-$N2zYI<it^?x0E7;VbOs}vtFYZ|}Bq5DPm8(=<iN)aJ#YePFUvT{wY9X%U
zOPTWif1T&N7Vn!08yGr}U2wP&RR`{ufR|;w*2WkYhlqunm1?0Dkh}132+_jEVRPwU
zG_Qa+!zBzGQD345chS=BpE+2BP8A|p>Iwt2FWd(M?nUt6!3Ti!b9E=Kj1xZ(e1FCl
zF1!V6N3IkMdG^rtcXw6OQ-t0bBcnvXJ{|Y>_4Nw6c3EJ>fNty^9Fmdv;R)y(8#8*x
z$)<uI12Tkl_6+1!;^x4xSkr>Hw>N=RuqZdCEA2)UuBiZ9LT1S@PlFgFKCEIs2PF49
zds+oWM97sF0LCO%@p6+RX0&v4((rwyu6)Dt!HghK6gdVsuLJ8W04mXZ;5Pz{g+vIP
zMJ}QNh$nAjVNs0*2`IJ2rkmjSY-T<l1MicZ-X#4m1U{MVBUe2^z=M6L0-bA5dXewV
zo4DrioNm75H4u1^`Fc?;n)=sW#n1yVi?pG_Kkgwz(}_&0*}J$9WdK~jww*iAfTPoa
z>PEOi=m~#!Y4>hOtW}@`AfcQ`4!UyX3L*c<UfeFmLy(Ka$dv&|O=@V>U5t6^P?5<^
z9{4cah(K=3guscn;(#LncVk_@aig~ZhM&;o;s+5!?bW!}OToX9@CU%Z&}|bTS7I^P
zqA4k=GK5`WK1H3CuU`4{&Gx^NZ`=<y2PiveeI{9>puijnJLcX!VIVuq=J1vJ0JLFX
zjySl8rw~BUluSGf3}EzU3ub!A)r<gaX4k&O(Z7LP5eyctSvd{<53ZFAtQt}3fj#A_
zzhfQ%;t^CXSTTOVKKb^`m$QQ(l@i4hK&k`F5ECOd#T-5#aus8j5W3x?7&^gx2#cs_
z93tT$dM~2YS}tL%lo<UmYY37A?HIXxg<QReXk2@rOkeyr<~}hBOl*+*iU?y|FHn9E
zh9qL-4+^S6Q!yALEhAGmLc#GDa8jh1UDWvJ@~duaREuMi0Kz70KMo$5!9s<G<#2b6
z8<!p|eh@OG{)fdc!3kuRe`Y2(x+{zgPb|%JI!+IsMfY>3-J<iK^=%b78=w=BK#1>+
zg7mqdzfOG+;OW(cs)?Zx*%1XrMRE%h;aMPCP#$~boHw+(DqUC)*D{ZdeE=@V1doTs
zt*Wb&ACx7-j974ED=Y3u9nG+3$;7S$Z6hT7wjHuRh7fxTFD4v!%Zs>o5Jov1{8%_L
zLMG=>lBsZTa5o<M-r~yUuV21Y0X#s;klngKl+Lf!WX|}1zx#n)QUeZ~+_s9D3kt$Q
z;>g06@dC2<B?jE$1$J*cI+Pi2NUy+7>czg~kwLc@g90Sp4tyxa!oi`QEHj0&Eenv8
z7Fr0GG%?+<$9LkLFl|YO1!1?z#Lc1rDH&i0(N-F^UB@M@3(t7Z?<5*^k`p%_)5ibF
z;zw2l)FTTgEib4*)T_D#QyUutOE)b0PiO`f=mnq=1(UOnSw2up2r6EYprfvaS9$m8
z{t4N7OzxGhlFjvGjhx9GN|@}W!MWxv0^!u17^jPFxMXU28g^z9r67g@(to1-Lh>R+
zC;<sbbr=qk?b{jIll2f5hWaHN*msWzAyLp3j~84Qm-x?{F4W6{Z=&mI?*w!s6lhZ?
z&KetpPLTA;Q0Sa5nmH7yY2Ag0FZbyi&}wfmOp<&Edi95a=x<m3`0<0qbrBOT4>6Wb
z0RR)R+Z_I#C<S&EjBetCaLRC!d7_;|@4@GZvp`N2(x)S|D5#BT*^UcS1FvB*_Jb!3
zGVt5apJ~a>ksj=SkA!NBdSfVgG0cz2zzmO-0C!~BnwK_pRY!Zm!T6s8uq1+U7><10
zV+jZhWoKuMjDCx=e4cALD|d5oePpSTHbX$FaNqro&yXb0eMn;gW##3&q3Ae#ihIz%
z-{QZJl}6>84y+*Wu1y#2Q*!-3@s+06t~s;Y{6rTzQIPpW$gKBLYaV;&7L7cQZK!$C
zRE9{c0Cv?7<y#7Ec0;yJhUiaBLfCn_S*H4i23#v4s9)w8i*XcVY$^;eX=+S016Ri|
zHw(&-kj6M4r(k+Vl&f3vB>q*H7f(pd=L4LrO-p7Y-et&M=;fpTFV@~XuIGPU_cssq
zHJ5p)ga$$=vx?GSDufh~N@kg-A~IyElw?XO6rmClMW$4yj1iHNL?|Q;e$PABUVH7e
zzI*?1e&=z{*^m82eLnB^>va#;eO=exzN=$md-orotK+e|x_&x<d}q*kf=pc9C_bc+
zLMUiPg1+Zta7|k)I(JwDR6k?wTYt$L<Lg)Oub`-RjOoB-d!y9y)96yEzc31_au$J0
zRrMw{HMekGS3lM>8Z}_i=z#u&HlG1aum?-+W?cs@qzG?oZ@ik@zLl?xkm$c91s*zd
zXs5!7T_c-t-;@{y`%EFssq^ZskNuV5yaZev-cRRCh5rST`n0L;OZ2`0Sb@apGm$NC
za-&^OC<$&c?}DhhNom**aBc#i<^lT8zlBbRSgbvO2y8>*PSc>~wO(ggYxQpm*-xFR
zB0sDZ4??()R3Pj2w{xY7xlZSUO<e;jLaFqD?9AfR;WHOAy;)fBxEs~@b$UP14<Q<r
zmVwa|d~2A)*R!7O$hJC(bFsAS3=ya_rr4D9{Ov_fYwDBPy^IsN48RMYl+R>_#+bEU
z!r;&Zo=tB1r9*Bo=fQksTc*-+CRZYAr7E~WJQ3pv#)X<^w&8`&1r%PewEKLNt~O^j
zBaARR5S0B_+rHkU%iYTtYw7=QBX_N#Sdl<A=)p&$c-%z$1X;BgfB@aZCa^au#vfom
zbQNdMEWL^)hxD(HCQMbHSjfH4S^7MJ=7a`Te83|kZ*v+k4il+;`n=J9gYLHWuR?cS
zKzECVJ1;H|*tKp*KzG&JrHeFhGjLCg^a{1!`qc%Y=v>aY2<2&{)&>O7kY6+yK714N
z6HJ6eGeu`OjTkM=-?nW93~5DSM;%bpwRz)Dq%dyQ7kRcQN|EHl$Wr5FbIO}?MbEW=
z{Ryw~@iS7s!9a4s00O-q#y8TDAm|Vw0$7V!!co^*+|>5H!(ClLKhw`Oryea(9oPO%
zA#=Ni)aj6V{d#RMpST?xfCwS~!K+gy$TEInfUI#w3_kv5Y9AY}!VxUbIa^JjPO>t9
zuQ<sF%Zt(#3H8X=x-`oW*QNmsh?JJJd>{5W@9Y`{(lK0}(Tcd{CF|AD7=c~_&9{GL
z0%wxXrrx<TRsqJ4D#Y*m)-5xeJ%b?F9~`(Mi8AjzLp&NW@|nf0=R!Eh%-l~0sSAk&
zyj*#n!@OU)GhW?|JaHx#+_>`6S+~N6vzQ!8KT^3<Dl>`=aTa?%zVt-V+2f(Np5tRN
z4apTEtm)IHS-v|ti9>t?>mN>{+t~~5Iy7?fXXL|I&*~><H2u!doH1_Aeh6>d`)G{9
zTMUndbiahV2V5(ngiqs_nKvTRdV^^loi$aa7vDZ%88PGvb8oqt&|bKZ4giK2dO%7m
zZJ$;&_ypXczj*v~Z8AOOE7AdsdzR3LfW?)OI)pbPLLjo8@jOk%eh*@J#01eiz&RtB
zw&F6!eLxW|6Fc;eyqG2&FsNdHW6W@i0gGcCQ=5zD9Q`*=MF)GARB#1FUk!a=ES<OD
z(-2KVuivRX=xd(aZRi|y2Gih9FJImljlQ_qP>CQlp!;hHE>iausC0Vw*Q7^hW;A}<
z6R=rnMnS6ZLKBjLIa$4j!;QaC5^npAMEfm`Vsz7F!bw|IRweM_!CkIV)r&_APug|s
zMrD^zzMU)(A84Q1h6RZ-fT9@Kk^SCf#B?G0cR#ZpTTat%h=8avbvYb}mME8Ye|0M?
z3q5seG!w}L-5C#F0!ZKG9{kZ`Tz~x7`u(t+!9$kq+5e%qKg?x1awIUVD1~76sEy28
zzyF&qjFEE47eY&<o)Q5dJo_Ol&G-C6ihF!qt@JfI(jTFU7w$E6hg6v`)@aA$k{p#<
zXa!&m!P|bCux5Zny|c}#pZ<RYv8OHZ0=rh1j7)r>EfJ~{x5^XH9u_4bKol#3J`Wvr
z(3tk%kH!fowS`T>|DrsStt7ButI_@_Hb@<N=8|#k!gc@$Tq%*4b2Y_c5d-Auv@pgm
zJA#t{q>F5cu^z0Bp0q!N_c}SDEAko|r^T<C3p<|<Jd`#Wn<b9IPzo=Rff4DU>zkI0
zS?cz(M;yf_JSjuIj#wT*TChF8pgP*GxD`(^F%qL7`D8S56yprXwSQVvO+t+V)lJl0
zF-m=ftWjJ|2w;Fk;`*qqy%nm1);JT(U{@Kx0el%0UOar{G~KQ*j3tY$_Naw=P~Li6
zcMZ@^-SX~#gSR(6(!8K3;M*h+7IYEfio*A)a?VnGOfzmpr9{>;#_bHt!NXh<PWl*}
zd95KL&N#bq8#V&qoWOr#`v)cnwEvor4X;%EcHuQD{Ns7ou2Y9+y@~7Ly{n0^k$zQV
z{qi|@a7vESVUC~!ZVn*es4AQ!O7-j41lv}`M@61$Z@*)*0AKT(5SH(ULRk^uoR3-x
zO+563LPqI|t2u-XJfTB+e>+YJl2VQU>`I%X`JBW!qV;WIg8$}l+UUF+BdvO^>KKBI
zqV)gI(D(eZ`$<a5T3vRXYi8M&c1S!%=q#`Bd*cwD3XrL&S+jKRXzW+RZDJ#ow$<%d
z`d4(jRbGn6$DZkEiMuT$#L&7=IKE$~fx>lUJOFvyUB<g`pI#RfYz3#IuCUU%38eZI
zwa>Wk%&&7E4-^YCQL#gQ7c&=PzR(T6x>-(J;dS=h|B(88cv8;5leS5rfp#sN<Z46v
z0e4tH9fTqLiF<2K;&p~{UbOh2#c`LfQ#ee&8}O)tZnD&5z>FmUOVkGse|6~h7=Hab
z)0`;RTyv1Z%T#e<5Q6xwIhag(_l!8@uZ@qI9<!Y`d3kfE{~Zo*Y8^14(7Siw;m389
zX22-nkeE($XFly~(nB~O@-`hD5A32WiAIjg-Mo*-A^;Z5y8%-d*jXC7R()5|+u$cl
zqn^5K1o@H;KwW#B_{_{&AawD|ff~|_sThNLm4KIa1m}~~UIx_cJ^S>@6~YSxM`nGd
z!NrbCKG7zx+j@V|(If6VE*n;<nM9<YoC`UK|I6%anK%jnU-J}k(+1YsH{kO}vC>J=
zFgvziO{CAXZV=e7+<5DLWeRf;|L>*0T6%4G6dn<g5?jJU?XYH0ayY;LKTCD!uYKE0
zt9E`(nI5AVa(uJat!?a^#;Pf~%wPCla+}frBDYa)Y5f$w8f+(VGD}N4am{c(GY-V7
zp1|COD@UGPVE5fS=v>-G_k#R<QNqSuI2sm)MDRAO3FX3vetuG4`!)-I<e{=!bJ%dT
z7EGhi;(1X7gYj|xHWJ}QyU64mbEhuY1QH%ySq&3ccR*maQSRU)qo|gJqXsTECDCmp
zxl%OmO}8>4n6`wnt1}Zycw}O%zgx%7CcDXIaEk?S4aJ6*5ewK*BchBG@0dsq*=qal
z-OWjOTA#}q@GKyD?leEF<FaaN@rz|yJ*fqtGv$*E0lcol9+a*m5F`GqgwfADVhKw~
zY5q;v9zH92R4zCKUb+htdh{dM(uX2^nn7#Cj+DPh>wI>*?C_<XR2kd8ezRE$r-WLE
zJNj&$V;G&7ID}+v%x(%|42atOhYznY+r~S@-oar#YD*m*9VSJFC%5rL%*|m8QzME*
znjwUkumJF5OMieMfhxPyGFPjq^*Q@1HDH{sWm*AP;S8L`=RP&;30|l-k+VWoU4SPB
zze}i;yb4B`_ZdmJ{dis1rS+I8M2*rTJ(L5CUstg@7YBa?6zhf_;^vJTCguirEq1^0
zp3D>CKu+V1U>0BnL!S9mShaIWt7q-F`bQ;C*P6q}5|Jr&$ls{sZ=|Fsz-1G*Ac2|_
z?C?+0s@ddv@#oL`onJK3O09MrINZk#iHVWdJ5AX7`w6Of7xvPM40iq1=lT+L@p`7u
z&3Rjy*E#itC~lg!${U|<aNga6auD`=r--p;HLKM&{NY?4;CtNo(1bt6WbSpvUB!ik
z0EeoO_&$T<yGPya&Z|-#GRZYIIy&7QzXu$7qS$~m^$h4Wv|O)&PT119KG?pYEphoO
z?0qtoC67UD$B3wFe~p~$+szcxmm|<M=3zT%5Y4JD)fJ~*T<*Xj8Sc}A55k3Od#0E$
z|C<|Gfg%-B^<)1@zOFRu0i73zOr0{8Y(tlPgIgzk3qFkLi@Twik)8n99k})_$cDss
z0M_Z)-EG=bm-4R<juHlUOm8r7_)=7)b+(=Hqt^~qd~lf)@Kt+h<@avMtI<3k*@M$q
zzM-}M6dDpC@sLYIy$I3Em@0&GzCLpyv^)Ii>oXnzKbFM^dj>2!nb{M<mY6x=u`O6X
z3J=P9zptOmu@-_xXTl2?2TaI01eNM2GnRgO*=>oE7&QXg^XtUwh10{TrT0cprsc$P
zv}IKYkpOya7jS4k|01Mwyp!e33OJU#td7&;Qp;RsIwiLp#yxcc*R!X{e_<UX9OXZN
zd?Xru)QD&p6m7AmDiMY4#A#xyd4bY?cP__zzq8nJEywXPncL0I7J-#PWN8c;bAgC$
zijR*!V_M0JK;$mMEIwoHoN^CX$m$br(6=GX->usPM{6S@tEgtuL(L3EEq@LP-g5kS
zaXSK`puGrPuus^B;5t$>aQy_Cr$EM9inw?;!0iPs9wK|~?E|F`7n0-`+ok)F1rZ)$
zS~q{b<M8{cZ{Xp*58K75p%*9brgG?+wOBnl@bN=JY~210nfZ7An1NBbSruNS+uF5z
zHx;JQ5E@CMXi7WYMw|SW$!3QzQSq<TanbrpH7W)jTy;Dw9Gsj?VCyL~=&=}xfuc(c
zKaqh+7eOl&JUL%0eTVPksuZ^&+5(5f?pB70-Yw3woP_Ox`RU!a4$SDLI4^b8yg~<Z
ztjp8Ws(5ddrraI$B5&+D%a0U}RCDyHMWoO#Ed6*z`A-!L-DlSTJ;byy?G`{gkn$WK
zE|8GB`g65E^}8M$qQ0c6zzUwjzQW*fy?XSpr=8=>n?7s!9j04)8Oq`#oL4;8yr|R6
zPX%E_(%McsYf3&NFnp~y<Y_Rt^`wr}PCMLBFpQ0+C_#5lUcLf#Q`7{!2=M>S&_-=-
zzWsO9X~ZAY$&A5@;zg5%AMyK|9koQG%8H?MOAaC5ToIoY^H}aZ{M^f639#{BlcA91
z3@h9tLtKh`X1pB}O5e5tfW3}3tB0OmokOzl2~`~f08)@A1u&@b8-gtJ{oI&`F|gDy
zzZC+z%rGED^kY82d-6RpJ^Y^l709bOI}pTY0gfBa++7IVt{`lhA8nS7qM7Az=$vim
z^)NV8T5Y8f>J#7*w%)vBm=1s91XM^t^R7d@6K9zt-vwRBu4dke!<a+~X_+B*V%Tb?
zB6{;*rU62U3W8=E9$hPjYWXc;`t!=`*Q+ND%i{MBw?IP?lCX+%<WMd%ZL%{q50Z(<
z_1rnQS%uEwd6a5v_b>U2iXTIy>iA7aL5v?*O#|7y1<xDL%<O=vZdX!M73pVX!x|4D
zd}^YA#Bbs9R1>b!*N@KwxHT}x=xDm0Z3mM}yq#bdh%lAvOMSwoovK#e7CU7M{^M-(
zfQbjn&ZoOIsx2md(MxnX>}p#cp0aXyHu-Fzd!_BOX~#||G-%++!~|8HKR@9#)2O(v
z+p>j6h8vPuRtOC;rl*r;tYml|l;y4&Wn=lTW86y9!=u05<>(C^IWjWYfnHlkp3k2B
z+|{D@uQu3FZDpo}6|Uyu_$+8xESKp6TK&!PNpjhXic_ltjH6@6?B0Bhla;a;y5}DU
zp8fE=$q2FzfYA#LTQx3}Py-l%@Ir(?#k+s=`n6B@em^KO1tw%<w;uADXcMSN!`753
zGS8JYbFfAv!w^MZ6&5yJ3kQ)zC2lr!-Ixmbek$j?PP4ba%!z>QAg27Z=S37#x4NCZ
zjU+P&AR!%zNR6q*tdL|AkAQ|)EkQ<;J`tV*4T{F%smhu|`OEd2b!MOAZJ@+@jT*^z
zEsm%xqpAE^(4A*|4M+r|-#SYBp22~+#w1gW(~+FPiaN-n$&LT?A5n&|c6+cCS&z#X
z)#D+E>l1Bkqz48(IkBJ>-K`U)B3DSLhR|3^-zGjKP(+(ix=}|NaBXnvZkv+ws~|s-
zvK6L5+}&=c4ktW`w(M3-+|G3Dv_`&Y4csVJokV#Y7g*MFod+!n5PE8?>c_WkAi`G$
zcan>Rsm~+-t$sS1l(p-R<q=w3ukDjptNy<Ybo+uzRwMZz1-UN&@n$DU0+L1=(R^#<
z&Hr<#t2oG=K8GatPixV+J~y@1kZl7&h?SiX<-ldwefr+HyD$O)UFD4NF7^yw)1Sdh
z8rDgO{+Pp2evYM+NKAUNWZ^<pHkN^Pph#WE6q~2z_qawfM3jx>A9Sdx96#!TE;>35
z*NOoM-leoBLN68zX8thUrn+$o;{-7UmMFrnkcdEev0&*^9oJg+NI9A61wiz%=ZJ6z
z(Xctw3(8Y~ywwb*glraK7+>_U#`w&VXADKm<99Fvhi=Scs?o2V0VO=E0D#dCp_~%V
zA_GNOURMZR7})tQjzrKT-8Q>1w{Rt(7I1aUUf(tUJ&zAT3m}V4=y3494+9;LD7Y2^
zGzh~+45%m#OeRbSU{o9<Zm{FRJ&qi4O2~Od`Fa?c0lY#cAa7+nNbOkaTE8gzw_(0G
zc2FWor3;oQe$4Pw|7&nNpLB}u%z&TF$CgKDG<4_?mkVAv;37*s0uxDSHvA7vZ<A>Z
zhRkmDTc~QKuo#`HJ%)6snMDW+^s#~01Mc4`!krk0d$c1jSu9)`D!u|(r0NQDVEQK9
z31%UV*wexgkW#Cf1aCx4ygsRLXlg{K!V3!B;jqvVLiRm!D8Wq(EX6BwB0UJv&HwoD
zDN=%?91xocqBSkAv~c2J!=H!2I)~~A7-vLBUNrKXR^ci;Aow$95HLJ^{Mdw=@7c@o
z1Ry%V({%Upmf=yz8=zc;5V=>Tb3nBgPi9dH%H`nA0JRBzPIwr5_#f{tc-+Xj=~#>a
zRkK$>JWi-IC}66)CY{G3E+5b*vtP8PUTusDTMJ8w{!NT*<UE2Q1~VCh01I#%umgpP
zKC<Lma*)ysr0VwGwX&<MM<QS<UYZ9BGxvxT{{YHqAh2O|uldeGoDF}%yHXtV(6t>o
zt)8<}v*WVojt~52JU^Bq`br?^T<yeTs}$G=q&VHd0Y=9w>Ny#yi3I0U-U~y`WzmZb
zgD%lPQY2!URe#Z<;_0d9@o+@Hs<A-(AqWnqe9sW~gs*$ixv^8lyV4CJ<&cW6&1m$A
zhYuJ@doCTylaAcXfLHhdtC!r}cjrJ!{2|0{9Al*m8-GJM7U7Kl6WxPI?nKe;@KxBd
zDs|>c)3gI<PDuYOx05Y;eV2Y{2^Eut8tg<|PmV$4<h|qepiLJK6)2re2v$L;JE&`O
zzqhvDxQFMh8rl40=Z^dCgv<=|+HIMc<dQt8p6$IsS|1Kp{vA8fZ$RQ9&!^Fr`;$x-
zu~ACp$;rbh$#?D?VQ>u#UN5WXvuDo$dd*%h_?)<k8lVC8b(la47c1$`oraVV)Jit?
z2a2k`I6<1-(mDP6>&AV0lQ$(zr$+vU=wY>P*Y_Cn*e_xS&QMjZR2Z(T?CV#dRS6U!
zX2oJT?o2%`{DW4lG)qq75It1Frcf`Lxe7W4PEQOF%Y1yKnBAmjrSG`7gt1QVCGQ{l
z966N}2E4<A4^5n(dEV#K9=H`!ujB_?>e<PC_#+Sw`%ePl+Akk4c9UTUDmvapr}uuj
zCuKig&J>H^(^v&(Ls&Fbz>OvQf_lS?2_$wi`_WurS;T$~8Hx~289PN@YxgWW;fZ%*
z$lj9qX#2!}7ECGhP7?LmAB%RlwSLD&d9gOYXi`Uyw=|I!=HrJSCW-$KhxB#}Xy8(z
zGK%XBVg1VE$Gh9;&lBy5%gue6x2|x%vkA3uC&oVW?*cO$bur`4FXzs_!7qSJlMeTf
zwQ{%MSm)Gu2rWnaKffAe{Tr>a)NPU*PJkR#Cu$p6;zk_ex<K9Dk@QW=r4@d#=_iN$
z2kmhollsB^92`h9pop@m0v@$ENP#9E=FuZgFbviOC6$tm_C%^4U{kb)!dQb~sqyt9
zR?wp(+!toePA)Ap8kKhpOfWr*y>U4H{zV!Rw*z=z7{?8)21)G=v*z9|={X?<N9r}1
zVlBq7Mpx#JSD!Pg>a6XSvqpCthqnS9sE91V=;4|VW2(iVLV~8ytzbSti4@oeFGO|#
zG)xZSlmDlQ=gX>zr!kd3HD)k96=l3o{qrj*&C^-ahc004e!F%5h9r$XnMSd7AJrW|
z7v+C27b|UlznEd)e(uqgV2`*@CKI&n=p|}$pQt#Fd|onS_?RHFAA!c6;Vd<|0D@8=
z&<Yie%+MOaLCb)-EQ1QDo6Pbapg6+P$7_Gnui@V&<g9uTYSs)uGLV()#P6Gs?I8ik
z1ZZC7`6~o_szzs02G63_A0@)fneT?5insLJX!7O33-hhf>5r-Kz2_GMwAAYYq_eE)
zt;fH5f;bH&K)qLA-H<VBCv&sP_!Ny}b0Nb()N&;)?$nv^<CC0h7gfc5+S~Kv{<V;A
zo=}h1Dl3L!oJM-?NJLRBmJavt3#mPB%(?E@0}iI!SqV*=DS-K@?w`y)bl?Q33O|Y`
z!gj37$Ui7Vef|7I01R4{9<^dBPwF2&DNroa*;<clP-tl^xky~2@qNaFVKkkY^0Sm;
zicEw^e?f}jt{BqPvd~Hae5r=Yph4|`g9N>xXL5m<LRFMUvy1&xbGi@u)J@QP0H#DF
z(30il5#zN*mCgqNBa&6wq!tHub0Pt+tgO7ay432V4u8UsA8l!KKoz>v`+Pc_R&D_`
zg+&@85f@-dm>O&&p<WhP3`ZdftUAn~94V0@(;vNeb^=Q>ImeJ+48hUF+~?VWb5jtH
zTmw?$EI|WhS!`lvPwEaxzOq7xszdg|1MBKow!#Efn^1a`geVT<oO_Ge%@sOY<ez26
zee>ofT8Xy<<TLQFK-;$SwBfJ7?hE2yLB$%$nS(tTn%O*w@v-=RSgqp2T;Wf{N`eNj
zN#Rt<rbQ}%qv)K3r%7}5%025Q|C>;@<Y99yEtJ}72uaB(L#=;P&*gt_+8=U$!+V|w
zsLwSDoJmk)p-X@tDff$XA-|Tx3j_$16`xQX5?L4uLgIQ;gk)%lp>BZ=335(#!E*2$
zl!4+5E>8ibhy!&lJh>h8WKk691S0{6DbKE5yJlLTA~$KyCwdZDR4uq1ohvmFld<|a
zi+e)@mCb)V`dY4Mx3^>dK|%cA^f^YUxK=yAPV%Ik)MdQ|=V?9tDd;rl=BUD_f?cp{
zoc}Cd-FWo8q1!OHll_ql%NPuwbR|#|sm+NC+O{_s^vFF1ekMf<7sl;peiyRE_?$sj
zy~E<w^WQ=Ih-W_pD+EF1x1dmhP7Q^OxT#~;OIuqJ9So=+^Xw3yGbl+p1qKSD)lpfy
z=h?Vpm?R5O2q6UWJcbjSDB|flm;d}4ZseHUG{WD{kJ_*kIu6=V@h{JB>Fk`RwygZt
zalQ%;nRW`g5ANT;g1fVfu-*{s1zxQNzSEH%ZzK{~XNt|@R!k)sBFZ7-(-G=Amo#Q!
zz<8Nvar~6-43O<h02~2l!(&0<pFeMt+-f97Va6jzHef`~6898Jzi_0m{GW%BlP8$l
z=<N8LF=u*1D*%5c?#<UiqkyTN#M2ZZ0q;}zA<r%y<L!%iG`;i!hB7X*pB+vC^^nVh
z@=T@60zuP$l_mb_C?1KmA4mJmW7dfDHH{kyky@>5*AYL{X5_!C#;alWVw(SMt!@96
zuss5~T@Ea|W)3!jphF$pk-O}FHYbw30YJ5-3HpHG{!61;lhQy8v4CmbGKnxN*P=7m
zLUxUS*Gxwdiv!knkUfYYhVZG2a+@d}IksU|pzmU}Y5;CB0i4J-G7vX$_`({c+f*ah
z!V@*YmxMtWHfQLliF@a?9)$o?c!mR}emB^+cdw28+o6W?=P(QhDEIFUk6V~qpi%$a
zilFHY)VhKh-sJvnpna}}3y6`~m_i68O~y4ee{^JOm!{gL#3CWl$^FT5Nq?tM-u;2<
zZ_&?a^L!n%{uk839|24Kn|a~gfEfqM=1=NuGA$_hcWn$Lt2B+Y^q=)UyTS(M9Wgcf
z#%_c0hx-#}cH$`b6Ll6fbhFMQR1jxzHPuepJxt2+&@1$P6npyf8ISZBiwnz_|Cw>#
zdQDX_oh-&Z?}3>={Cv%J+69O94_x8P8~U>^81A){z@<%NE%v(FjajwTBCh@am~xhf
z`W5<yhO`K<Ie?WtIEbjyE>(6|mDk>S?BgMyM|avgQ>~=FL+?;kv!PedHxKbv^7YkM
z)-8-1KgG}1+%GiLwwc<l(3SxslGAd0uc$QX*>l^K^W{0#Zth?AS1esTz;eA!P+opu
z$%jjKp3VMvY0#&i2V)<X^s=wU94UmZn)rHjOsVhBa=m&nv4^5nPCTly&R|T-CZ<YP
z;RcwF7$LQms7K(mu3kM5rkz+3RCCqKXTWT<#P87<yVfj0m2F)>N9m`se$BZe<I-9)
z=C4QWNr;DWWPX$4v3~id2`h|0WH`!7Z`{tBfb~ez4y-ESk+Tn(R+bgVwW_n0#yp$f
zNc!9YP(b9LzhtiQ&&jQk803f|tyf+0Ke;WNu^it-J1yOA++_1;>)A7BE<ij?#M(h0
z<~<~J0o?|v_2-=@-Rn;~+k9N-4Y4*VjqBx<9;>;9497sykW6V)xa3L1_^tf(Luigb
zx|yxe0uK^Lb~sCijvO%oGKItZ8vG7=d%~D@VXYz*SwNQxCI&*L6EzYy7zz@RImn!e
z;ET6VK%LF=*Q17{Xz$#+w-U1*0-~%z=Mkk}wrR3zsSEp2ckyjyDG!>ap$J2$B$6OK
z0hq|%bW}}>-Ol;Qs$@)<lwZbt(W&UR9fE``kzhrL8G!+IpdKan5u&o}a)0_s**U)w
zYd)e-4u4aA1!z1-hh27=%2kv*402`lDfnD90E}0RN5qGim}&*&Nw2Y$q3y5o;zpzq
zJpIo->^e5raD1%F1d|A(A&%c?DJwe;re|e~l&Ze|=>8KXm33=euh#sl!`qpP;}r%?
z3iZ`zwDE-+B`w1kYilw46XR#u=goV^iCl;y;#P}FZ8|O&u1ox!j_Jt84N4oKO~5Xv
zjRyG?4>(Rt*tmm^vbmHt_B2L4AT6ZY>7XD8j?A<|HV=yLO&pWa3GCP$0BTkCE@HkW
zus%JXOIE@l0SI<izqEz872IjW{Pk)T-5M~NLSZopISJoYcsQ)qvKpCneQwfsJf?K}
zW;}l$5I%&9!itAYlyMf1XAu&qK~yIlr^drdQFd~PkrHp6Bl}~NhoNzJMDv`K5srmN
z)21|7k)D^L6W6p}Est}#A$pUUU@c;u7+UtPr|f#c;o&t?gN~c-bTGPggmR$IF)x|k
zaUx*S+-xy*^_PTwW1Xaw1WkrjM*VT*sViNSpvd(87D1^+gD;jQT-xd0##lA&vB%CW
z9^YpfJayGp9UpdTd{~gmPn#yI$2k>{op}`|G#~x?_2XPOCO3%zMU~tF_82uQ79d<|
z*&rnS8{-^<%0mS-N$E}fv)szIU%WU_q%uT|FuwrfY15~BK;{v=nr}f8Hg_3=J314T
zhPa?`3_|biU6b75axBUu>Kcq+HZVS8$(P2$_3tU2Wl9Q@*LdjA5YrMNli~s=Y-|Rr
zz}N1m)xFr9j<iV{Kl73mT+|yoJB-E`h2Gkrvim(scAgY`Yddimrzewg@@M{0l(Ocl
z1}PbW%JE^uKL$X_l$RuSdr<Zb61qST_2(kX6jQ!%FXx7I0wS@2A~u#A0Q|5Ab*Eqg
zg^9mW)2>AqFdpE7Pn$Py6p*zTOL2)^+dPK2ES~nzUL6>Ol!KA5xj-DaDBx?!vJNbw
z9Vl4Ez=xfF9%BDYud8Ky6QH4<f`Z!M!3TMY_n^j$VI4)e#l`s~b6Ar~oG>m^4}JZB
z-JXul&K4z7O2|sGm|84A7U2;HE*VTp8G0IfXjSwnBYZ2W%Tz>|?my3cLDVQ4k#V<i
z|5c&S-<CFxj<ZH-^&(N~^5JPRWDrEN$L@?#@Enxaj8xz>kqcBBkDK!HxVKK1E_Kms
zvo>lZKL`L;q+fY?HzAobG3m|DLN=&v1{@anp1;A{6txTy4_``w@<f`){JDrBqrgza
zL8JA#(aDKkhc&*~THctRe0OOMzS|6uK!(&{rqEm0=)r<){=Fc|lrS*s)^P|SmL`L_
zbvk9h$PI97&$v7aq-}t%<b?DnWKu3`6*{FpQj#Uf3?AeNK-9c~0Syk#yY8@a%7f-R
zivLWXF49@53gOmqD)9`tM&1)>TQ_yQB~2jf{5nGvETv6g`Y*fqKsIge%&Ne_wkh-$
z*d$c&IlD#=Mty6i@D9Q#1+oM9rpSnyDMPgA>O4;;Qg$3tfQiOV%*o+|u>cL5VB0xm
z(D^td9hv(;A&^x$d|X516clQQDdyA5;QMF>jIuVN9RZROr4BVId$NsCjrA`3eB{Ha
zWA1GLkEOxDLGv^d97>WcG&BT~-6uP4SX}ic>!l>EI^dIh>((?Te`4WH_be`n*SK`T
zYZnzGD{grJHA>e<GlO6B>E$4-FIl296iDb<=1Q`u3{bGCB~nWW0_XM(2$(Sa=YxN|
zOW-*Uw$8Zk#NgMk{;1asifTxH0sUo1rn;2=Y_c~cZ=*&!`Sp^}|1n`<sO<q+4r*5p
z?=zGy&I<3p=$AFU(RbGo)(5`uKi$k+`xujQcR&8bnDzjLJR-YJ0fX4SX=bJM08^Di
zw9R3yQ0BAUuo~?-8^vg}HlcE&yWj#5Le18TL6J-T9l8V}k;&-Mjn)E$_k?~>`0`RJ
zKUDO~bR9(X8nOipwG8{*cDXI=9=>D${<ic1yyaa3f({<MLp>6<a%%{mS4=W#!nyP9
z!S)!>y`nKoFFQ^T{Lw|jlvIatp@a>Cgbnu?%R&EZqS3XiW=`c?p_W6OZrr%BN^A^p
zm*|+d0VyAEH8$!mx3FF<uc9e6>r-J95ls2fByG_}Aa_-9?>C$_pBNpPxon1orI)Cq
z<>gS%+{4eD;Cury1!=f**RJ?nO`Mc7)!5Q^dExDK)A)C!S=VozFckA9^jf9Zt;Zq$
zC-l00jG)l~{9^cbk5-duS~5+LSe`*||4~-f3sVT5mn`Fej^LZy%6#{6O)sYRna+^z
z;{tv7)hVToy;izWahM>{U?iigp#HM$3Fat88O}jwK~z~5#0!x?(FJ<yb!zb;<U~7m
z@#b(*s--vW)Cz*6x{8WHaDQY7)pDFowUT*hrC%S6uKo^KmpkHn$9UMV<SjMG<=`Kp
zyWx7@3JdC1pIHbOaVSZH)ANQG#VFE~D5UkZf@Ag>Xcsj?=N4ncGZA@%@G$fDG)}Ky
zORmcpzmnFbveJnDE;uaAle5Xp!I+w&wSDt0L$#&50~%4kk^#*}q9|lyl23EZdfJ8k
z9dCU)wR!nT`%BTq*B=FM?h*N_s58-=k1(9J0dI<2>R#8>y@ys0bD00Vm%jdldG<e@
zOv19?y8~x(xjc8k9J{q<9<vFKc_&;#d4#?`K8Do9lPCs#8g7aH{)Oqd=g)Dr?V?x0
z0_b}C;4SYL>zU;Avz*Frk)_?De*|$676vqn7<RJoN{)OU(7b(nc6HQ4LyHhed>rvr
zqS_z#t}Oa25C3BF!wa>`Y+wH4?D+@qEa**zk_kI+u#3HB*|#73cDTYyz8B_#mT%Zl
zOB|-^OefcgM=I12b{}m=ScWVim=Zuz5>pvvo=>9`wS!m`z2UM*&ZjV`QK}p75v^~$
z!G)6nCsPsTfs3X&MToeQ5ZE!}jkGPRS6b2ayzP6KS7A<S%tHM#qqqPlDy%|J1;6@h
z+cw0g0`nq*2AXu&-n3y(Oa&NxXs)5R`)C&8T6n(q9&{X(pa>C-*-dl`C~uuundI8b
zKv%|#fcNAeClmnlJFNvx6bm-sQj`8?sU(}${ZaeZT*=~)%N9bujjQD50W&MRIGt2$
z>@@qz%?+m~DAuZBn6doSx?wow5o}-6>xxd6P-$MK0Fb<nj)33MSwo{9(MgP6n8-8d
zttGqVK$f-&JAe$gi-n=gCHFA&0-;ya(`zn47}Jp83XPEim%$`K?sWg&z00KCXC*z!
zmGGD7E_})yr#6{p!?RmaS>6xocYxk(-a#u8kT5UwpLXlc$k3D)b|yH6V3S-m%u!B1
zE#ec)M1~#8M42B9L@7jGGp6zN2uc@%30ybFg9o%&G}91VAqiv!ccH<*$`_F$iI~#?
z)D#|x@gO(wI<Og(G#%;Lq}>OCHZJt^k&VuxtAiB!@<K)QnjXAx(fyE)arx=qVw|#H
z1=Bdw!YmVr+YCZGQ49$D4K&R#5Q}xG1?IodF|K;v8`Gvlo+vMTyn-8h?8C(;21x`~
z>NwbsskB`%Z=9gZQMfG>KjlUp<kXA27<D9Aeh-$s^Q7zM%vTwVsh`*)(oa!Xy~@km
z1e=3enUPHsgsJB`1gp(?8nz{m#Xa(1I+a|bE0KlUz_D0Oib<4c;QS{H+hdJ)2OyI<
zZ*3-hhj$0loZQ@7w_E#lVf-uQJ;k^<ClC!>h`3R?c#4UhMmRZ0)!AUP740Gpu4mK&
z^puTxDGKehyE)FWlo=jOCdTq&K*T^uoPc4MYS<39w^yM65E1|gqcHzuHLSn?_^2$+
zTdt8Bh&QHztINESWIx^BUZ^ERc5zU-JGktG_lHln-Gv<@d^e!mDguc9yfij@GHzOt
z_ub#b@vKVfF@+n>KhBqF_OjNt8da+)Ve(MR4zb>aa~VIV3>XlfIn2&$bDom_Q-6Q=
zvC}75K6#IMJFPvXj#l{rjv|ux?MADV39yIy&bTqlxTcC~T*Ury{t4FpZXWMu8-KQ}
zpI<pQVq)gkD?*i`CP;#_?6rT1#+JiYq0K`ho}M03XG4a~XH^wGgSPgX#l1B76rWX#
zE$cMx;M<^#fmL~B*(cwvuk7YL1%c7g+cnxa<MeZwHssT_<!dyloOxejAtcKnxRs$5
z^{G%D_xfnu+Sm>pn34`RERKwTq|>hIEXXpCo|ekG*KW+6We=9Dp`!OHMhqDe8aj;e
z4<(>q%#6epBj`G)o8&OlbPk7LIFV_(C?4nygoQ#7=44LR=ooMqz@;j$6I*AUb!#)Y
zcbo6@1+4a46!-M>R_&?24JO~9OmE3*U?4Yju0QyzfWWY8$6Ra>Pr8&@C)NWzQ#N$@
zr=Lc$aR7L-S%(g?=&RrI&-QT{r$PH!(v%AjfPbjz)6<G$_BLoEl?jDxYx$8Z^d_K6
z6T@wHTsfF?1h{*e??COx50<6G;`WJ?o0ulj9R<EuswX*eOrIa`oYb{q8Vu0YjZU7l
z#dpqAU34ydghq_%FOB;}%Po7Fw&;CeKJ$g%Xb}~pu>EysZ1%hH@Y%E0pnnE<)LxCA
zmPIwgm13HG+c{{>4gQ}AjD?(9ZeBh3A})&(z~{Kw&eG&CB4Jj+p5nbtvmAbxN8<x_
z>UcNS`>=Y3-Ukmyv5F|UL<eM+x1mA2YsP63Vb!ufzKhiIv<8aQ(A^fP1ShX52gK2R
zq)Cm%v7Gh!e(k178|@aiOWJr~^!TW0vt3-ISHK(LHpLHA7*#m%aB-T)_dfM%$qc1$
z?E`u@>r(ZP4OHHQD5`I0Fqx-pHGb|>o+pgfmJ|vgiqcsBs`%tC6nSt)ES&uX72Z{L
zhdio0YuO4l+V@7)r=4gHSm5>gA3w+<MC<8k$dfxjy&<CKK=ggf8QkA@p^;7VM+s|I
zF_!PZoZEtL#xZ`4=0dr7%NCn@OjaDM#1)gL<JX~soywQNbDk<2y6AmiO@fq#Y=R*7
z>FBpvN<Yij3U}4}aPGC;+^3)mi0mE^L#U2!F!z%OmU?~TAgVq2WneF*&^qAFhXTk5
zq_cKD?twg#XhzDggJeE~`(sn)d0tBr+LpHLmh718pf@<cb7x$Tnm3Qiqv&W#VC0Zm
zN>S4$)ETVa=6l&8`(Im&`tv95ji#N|X@CDo%JA{|T{b6J*Gihx?U>)itqmrBc9V#|
zX)WK340~OrMt#FTPIjk0ePXZaQgr6Jy#UF@kAD=YuhY(}H_eSFhT)Oz$%U4I4Y>1R
zth%7w^uQb&>A$k>!k|H`np4pUL_o9_dJK_FW0B3IR{UCdr-r%4wVHma9@zM!gP8sc
zac1J%n7e~_MZ5U7V5;ppDSYr!fsin~lHU5oi*}4{WI-2*AyuaXb8t{%)GCL@tN|nl
zp#&0x45Bc&k5KBcJ@Kn?%A<23{|P+PGd_L*fwD{Y?mIbdGCSwR^U<es?wO88Q;jNI
zY{uoICm3upOhr|r7mdT}tdYl*{Em+Q$?2l!oeoODFI!iBS(`*h)vY-r`=n(ETA_h>
z71V*(^MGkGk7~-{iI&n_)G&O+_pEVc)!~7W>5RN&zksNd=w)0X91FFb8*OLmG;#ly
zczyx_LW~xveC3%*d$r&1_YYcUu(6(cEsv66D{R7Ko(Hc%EVV&xg!%)%3++<TzuT?1
zgHXCsWvD-h2ZscrU<2IA<WK$^slNx;+TcBkkEK<oiD|uB{%h&gL;=b3P~TO8K>8{<
zVNCC<#mq<WF73#eOO}~1;97(;sq{yzG@@2_oEIQJOliY#BYs#)hpHb|ZBqZt-++HA
zji(uHHudhf<txVFdQNPU{npfbb*Mk390apsCC2iCvum~$MMoF)-1;mfX;b>$ix;0L
z)J?9PI5se7J1^p5Bdw7tUtV3QNqkHuvi^#l4br4baY0!P<=HIm(PT@tbB)^3kO<<0
zi(c8hl;OjHdO2?P)atT1m&PPrx-8Nz$dyt=2;qxTL>4JRS4qBo8=mNQIXhHCmzF%A
z^~kF0nz@dLBEEiGQxbE+wVxb`aew*WnDdeC+e?>zPuy!WzE;!RR7R`eynBKNr=*Er
zGb7V38uMqk#(C+*D@>l38yfL7HsWiuVN<m|v|P@fRR1!@pS3y1uN5;5e}%vaYq~Gj
zTTCsth}4o{<3EAOw`=tCrW)4Euj-bLUA$=LwMPLd!g^klEZE`>Y{e3V?qk=T4ue+u
zad0878W0=A$3<Vi1v)Gq@hzGF7L(OhVZcZ-AW)+IV#{INIK#cPT#UKobx^32clzR1
zBqke#9Wf7Ld^o-M{Q&49u=)UALiILo+7!?-2ZN@4G6Y45$8XC(!5*v&V*}MD+lfrM
zlo&fksc(omd)5iMja3H4xIp>%U}&@}{`Sp(*gQfYMP^O<BI(%VU$9bdOG)lXm_`{G
zdSUO30iOfIG%G9L#e=EB{z#iaNY@IiE*w`t7KZ!N=FHi)X%nBie7?8K^yx;h9HXA}
z>Cr=20>EQnu=1^NVR3cjvXeS@e$9fLiAwvnG%mU{$PSd%unrHOI<=D=2!&01Y&*pG
zBDWx(iLWLj3-s4vFV7J<q$%ep-GFtk@Np_6<y;E*Y{UaX%BG1CMLz<tnULN1nzGG~
zmI9P54Bp5P$R09u1)Y+GG&&y(m|lxJBj}<mHp3@KYMcCv1S!0sF}oHT0za+gfTdmO
zF*Kt_|Bg%%Ivqx+`0U!X9+e$+SLgoy_tGHJE`xxGL9&phr9))>3nE{J5aLY2T-fRE
z!R-vW;q0c{-}#@Ap)P4tBeosbqL8W~R6Kxy<aB4h8Ah2vm<;u$$cJ3!RZ$6pg4Re@
zqVW`gYpmv!0=&HbpAch;e?RJeiOWQGl)7T32IjM1(W07%`1>GGBeZ^z?4-`a#%poc
ze*IbjN#(~7lxd!2G>^9`;+1}YMBybzREV|L8B7y>D7YFik~Xlh*}J%s(L7|*o&0B(
zd0i&Pi2XYi+?=cgStl-R>6n;B!S;vx@+LA^%ZM&xb!lz@5kDOek;3k_FeF@Sf4u#F
z!i{OvrphNpPKVoL6mX&hG9D_;8yv$H&)uj9u}H&#<uIRCc=<58q^|&B2zBKop1=$N
z8o6vip^foEK1d-polXVJu(&AKf^>(JS#+G`pRYEODJ#GndQT&kUGfuazoPc-J77S_
zZ?7=^Y6#z3_BBGUn0#R#SiKCFATkl%7F3q6AP=3q7t`c-N%`%E{cgS7oE&M*NEKmy
zim0NeL$-iYxrHv-9`ZXgh;`+L8R$&JdymN*1$}TtggKC6b-@ZTHZjDnhIX0J<u$Uz
zt<+TQo)g@;OR^=j8rN6Kd*p|j-yEra%+EA%C&s}831+u7%`HAgOczB^&K{balu8O9
z0V)_RnW{z0^2R51g)k2?BTk!E6(V^AC=iQw;oma%lH9_v>IeCfRA8k-JZiv=?A*$)
zI(?_Cu&T!UfDyDCCSZS>$D*NHYhz<$b2Nm{jUNF#JTFKqrj7u#>h<sPcs&@XE_$0*
zy(nlZSqoN8XlSVTiFuxi3<+5eqlkWaSDi8fL3-sL-w(G@k+51>w%lNbQ2#PV5I==3
zunkmeE*>?iAs{~e!>t3%<75}G)urpQJ{Y(<4c0#=R5o-2`7D4o6`n?01qxrcC@T(;
z;b}BsJeMB2y3?7fh@mpD(0;<h7dj$YZdZ+wYYN>rdMv?K5OD0LI?Vp?q3fmfj0$Ae
zE0i2fyAzNuDCvifAFs@rWF&Kw9Iou9^CyNhCx!^}cHlreKCHn1&=$Q99&BhZWlDQE
zysOJTo^#F02f>K?Hj-`FqLRZF0$iwSfi`T%-&CI{w%3QBV4}$Hs;d;!pvAc}^#wH1
zu_x82Qy>wYm7dk~X8#25%C-V5lLK|j-={%iM>xi2{h>wtU*IPtl|@$fnR*+`tLM<i
zZ~ZuSVMW)?gsRLmQ*KU}iqYf8`ax64hJ>Y804|<2>I+7CS1$VZ4CnMbN-YKo5`AW3
zyQ})eX5n|Ij3PY<SaC)Ff`KA4Jz!f(Q(1(xsKz~>cig0n=o=H*&z-->$*D8^8{VuX
zyEa|&1Gjm63dT19mZ{H6?Tj)A?uxS2kzohgAQe^;{2ay8WZ>O}l})?_{NS0nt9R@;
zv@py1O2#32EUuQ;lf3AJ7JuGLL*9${XOm?%GARbYVGoKj@TSY!Nq)7@t8;C8;`H*@
zC4d%t8ecxlG_?OjmT_n8XQduKS^Rc{k=e!4H5vVvu!BskpxgN!myY%KdNx(HY{v=P
zE4d>fyNOE|zX0F=6b?o1?mmXMoE(f-!~{vI>@}$N`e0wdN@Fu$jW@Bi-JhAqwfam`
z4-%CDLyO}f`3^4Dt=k^S8nZh<aI`x%`uZc)<H8d5)E#lF(2x>cWLrD*ne+2JUGbNf
z-KAuVci<LqL__HKJzqxYKex*4y7z+}#hPri@Vo<~dk+Y*Sh`_QA%J++nv!-53^o0<
zO6R6M3X@T6k;%k}+BMd_y83!O<M4tQHf(fhAU;uyzFW6zcfhFhGe1X0m&i9<Ya;M0
zWTuk@3j|kkSz1q|zelp((P79a{>d?dsOQ%=xAl&MVUb|gtal&9UqK8Y+H=p}GH79h
z)igOvy^^hr;oE+5FI*ERvcjn8kF4%*c}ag@Rh;|(GWdI7wUd)tI^4+TC;sB5-Qf}|
z-1c5u-n~edl<^cB5Q^1~0|(mL_>OHpW8at22l^ZH2t(g6!py<zXWX%d88H{Iwwb!-
zoB!g0Y~rGjmJyhKO?3x;DP&?@x_QF#FrrmzW~F{O3QS~DVpZZ=GKUDwz^EFP2>Zn3
zk7Q_nCv~^w_{C>?34x<ll9lvj9qMofMY`we>M9#kd+O?D10FDDYMDGWNzy!oX4s8M
z<YJ-jwQik4W4x|Bw}Y6SyO)2d3$of7eGL&sx<T+<aT@`67osQBYK3M`FwXNuhuZ_E
zIw3z(3WG)>u?S%M3pTW(C}k}X^Iw-NF?SeaX?f-5&EbVloW+B6^uZCJy3|n&R$sq)
zGn9uUTXGnUIbB{`T_Pg+++trW?^w!1&`{qtA9lCk<Af5%L~_6lUBr$qaJ-3gN*PXJ
zX}O8g5;U!xF#F@jkIw>OUm5Kp>|1(HnX45Q6}>dKJ&Jc8zmMo^g0Y~)X7V$gh|<f6
znSYDTrVp5`#0ksgF+m~@N&BeN5NuaW%k1q{g4TR*MZG0JF-cNfbU<@m9v*9gX7dKd
zr({AD#A=Q|tsbtd(78BYu_*D%rs=CsYRu^D^55AaB^9}|TkIB0;zy4k_BHA=vZ1lt
z3Fyv7BvST1Xx-8l)Bm&_yt*&`fvjHfAhxycJ@Yc3jHPyMy%X2{pqdrK8Xh6aiFMRs
zbmBQVIfsrO9nPI*=-C-CGO0#=N;Py{t@<udfgygGiim?Jaw-+~9-03IfjIG9*wj^x
z`S!zy52cdD6wL2^0V|$lQ$58Hg(*fKLZ7D=Ny23}d8#juq6L%1|DOQfYDlhb4rp+L
z?c%Zvh(1fuLNG2dKBA3QI@u9^0*p!&r>RI;Tppijh0f(#N=n4jPsvTI`{@Hii&;KY
z73eb-p!4D*O6ysTO_9E!oUSk^L{kM<oa)vAry3E-gGWv<jh|8V#>^Z)9#2#M%~)}R
zu~Ne@|Du0J|3QNe@B#=zclf<>C2^H<V)U3BZ5yJ7<!2rjLwWk;r3)4qP;&vM#J%yq
zz1Gh1$;bb~eiOzHGO{gst&;Y*!;sn|)7SP$wl<>Q?C^)5GVWN$PihV+8N<WPz&b>g
zEo21-($j#oWUS4j@Q=IiC{|09%|5$#n^3|4d|bnyofoGv)%G0PVOgPuodfhKxKKS&
z98&t$&uO%gtvc%6lz+l<OioP=5neI+BO8mUN`ytRR!7RqY(c&pSc1qFc($ggF`^_V
zc`L5TLYhQJA@gwV5r*6|&?y)n+3YWCwwU#nLhc~1+e2~kOrgk@cq7}WFns2WIx~-@
zppZ>KtOWb<$^DmN&enqeMrTPluftR3+c3ILWw6WWSOw}M{B0$uqMo*Gb?G}9mg@i*
zWYawf{>h-*bYCK>d4`F`Y^?<&IXJ|96j-pVvIWE4Kg9hYVGW{A67@1UZO7tYkta@g
z**%*<8;+=$;Ka(f+6dg3)^s}edJxSLwC<ksGW+thuS*4s*}$GbtIqn}$D_lU{z^;;
zWHbN)>Iw@}x;rY44c)=yw6T)XFzA6?VwvJX$=X7#yL-7Tn2_yoq;oO2#|i#itNxI0
zh-OV-T5yE~NEB`sG61QCk$*AM%60mv!1}6Br*J8CcXx*?BC>IS$N;NXc+_OSe*I-s
z_0v@_AQ<!t%^2@_R7~{RvR-P^{ub2yv_N7t!`=nu`=hornq<3-X&nVp!A@)2bBNUl
z=$c_u4zO+$=O!bfq<dwl`0eq5EiUQTwj5?#LfjNXZ~%#!50CjYesU>H-cmb8c6>yt
zHj&Zrj$6!LeE0V4>-6G0BFH%g^30&2Vc}nzIIx69l{W*XgGo<|-yKe@M)9_5^jDC7
zw9c5=K}rVqaCv28xjH$U>Fi^(lN)wg+Llnu$jTG)ZE0crr_<5VzHYZSuC8xK0*I>l
z;P9AXwk?`B?|f~E@fhocFHmR;VN+;Jh-*+?S?>+jnzwN-TF`W-65$+y9f8NL3l3HV
z-t$cVp-=_eG)~r7q#|`cp!`;uDOMPz#}=7vE+`7uSa{&WfNEr+fC3iUI{CcZ>f1Q`
zLZhL!6WRiac~_oGJF2GshghN%oVM;7s#5vltc=v;&<D814x#y>7G}}K@r%zjHZ^{t
zY{&nX+ws~G$H|cs+uxn|2YC$TAJfaNz}JZG;u>L^R)B-?O9t{&65YC;OEdu5{yF~a
z#m3qFRZnVfZv14;(|R%AZtm=11{TaLDW$Dx`SWm-temW-Ph#mrjLIzi&fmFub!dNg
zzLRUSC%5XnB5s|u%DxbNXOwbi^p=8`8)^B!{P^NPX!qhe)tYwpWZUEs=>(6v7v$+2
zDjNIN$9ht_yLGK!yU&k;sb<vR>GdrIGwOVRwYPiU`B67E>73jZ*5(BY&bZA5Fa1+G
zpVZcd%CI8u>nRC#16Hg!WvrqqfVUc_^yI4>_p&w4XMA(G&UXZ-G*>;jYO3FO+b(6b
zFP>Sqc*T|i3A)KA9`o-!e}wz0{j@1Prd3hv{u3{(QWg`e!scluFo&6Ryy8{kHlu#6
zF}KiP$(#%#6Mlk)lRvKd(U^%%7!JW$P@cY5=R?Zo9+TZO`H>g~`_DUKERX!tsKA<A
zs4}2p(BErKI>?O~H*fo@2@!{@#~+)t*5f9CMk&*peAbw9XmZ}Z6$KdBOt%342z9v9
zvY(rJ$H&Su;@B}+!x(NyFI@XFE_<vqVJ$aT#xnfK%tnoNP9G#=C8{7~nqmWqEO-d6
z)7{iZ^y=AD_Pq<YkSoG4ZU-$Is8V`DeR#rQj|lQN_y>KL6}A-}{rg82&t{{5f(`;P
zhx>!I%5_*2igVSL0jBWMg{(nsCPGxwi3@UF8on;ziYVxqcDTH}*smHO)s-ht0+<Z)
zDLuFi@(W8Pgtcs$%>3;K^A$Wmjxw)e#cU(^HrxzMro`G!WYZLI;-G|{HWiYA(#q~$
zMtdTu@|iwg^vi&PI(NIjzkg;BI!j_Ovj)gmg<dnA153RdJmuyIdpNVfQ!iJLD#{0z
zoVTOOVVdJXK-Va*p#9^6$(n_F_3K|Ds?gTlgH%j;73z0_4r3Znh?t*|b+u=B>C^|K
z6l@&eP;xO%K1iYNw4_?HXeKUNR0<!S`T%$fP6jKPM%o}@vJuo{vn3F&SwW#e%rPN&
z)7a#43-M+1@4GJ-2X<;PLF>4SvUB;}yJV)3IVUech(jVS3v5toAp6D|$rJDaI7cXs
zB8f_F^o#>p4I<xkihL%Kb+KJxd{Of<c8Dm`hagAA;<^#Ff~@c%*>rl60IDJ`-VDCQ
z4~o&WbOZ{6I`CvUvg5bv)@|B}TxLYUzrwooaq?eJMesa)_$D5NMVp;u_-l--LPwaQ
z=|D_!fHACv$C<-_J>~4k$`*E;N24l)pExGs&`77t^QfS}fy%RfRdhf_A$sD~#kchp
z+MI@tN3=~M<tHa6FSA)078-hu{tDVy1G0~d*f~9}_<MUMOl7$pNQkh17)dx`(IRd=
zG)=zy_GyRBh&^*=7%mHp>#&M4BjwV03edP3uxZ5pzD+1k>8es5R?@m)T_I%Ys(q7`
zJ`}VNW^A<{K$n2aXU2nUHE?+kAiB=ox;0oUY2y1F+I6um!P301d*wx?zPqh&f>)Pf
z_s(1_4B`3eif>PNBijh8$+00C@I%Dq2eGjTvPKUsg%jDiafc4w{YjQAbPePQ3Z99m
z+7rWQzOA6#%#xsqd3S%k3eo{Mt1KJfokan<Q(s)?+pSwYe=|im6BHv#KoBr-p?suz
z6+s?fQNSP$0T|pH3K0g(e_(_<^Mg9X)C2k~9;K<Dx+`MlWotiP<^!T>e$0r6yM26A
zo%_2z>96qpQr9Ch4_!liO>awvhUN7Zu-+b9dRMni`T>eA!1}4Dm13O(#@$3GbRG{`
z)fl~;=f~K^CCk7<9pEH$drf{a>QxjmEtE65QHRTGtGk*MczoLY;gaUNUGN-t&6es~
z6z8@Bq?`gx@$T@j0#2OZq<~gpQVgJ-bF$PaNYUm()y;2Q?`3FONTtWgnynxg$n*i9
zg&s4Ky<J_N##<>jcxr5UZ*SK(w|hrKck1J~u(pQPaI-c?9hDrt>Udo`O6-{dEF>;>
z!bri^h%sH)1}h!?X3VjEc+k$O9Y2&Cs1(@G+`>YUrVPA2)FFD+LI!hm$!v8BLv_P+
z1EXErnZ?U3!{=>{vChlQm9dSI&5>HAFO}8`7aHQ0V2?~yAUF!<m!96mSfn4SFK%x4
zzAv=5L+WHw(Gm4O0^$wBq$O(cy1RU1v|685b+2Y~Z}}QPRwGBsyBqwFuq!15p6V&;
zq1v<CIrcGTQWBrMY8HhqRlEp_xK-W8j<G)7%`wWkg)xW<)*fD&CoFiboFoLWXdjQO
z>D%pW-A94gi2|05h@<1uUNMdJ;vWN`sou7_w7S%n>xVYcgtwM~p*OMhYeC77ewl!~
zVFn?G8yj8N*&%SK%=v10=xY{hhy|DO{T;4H`QX(>waJn%Qiu4X0TP_QcPfp9<%phV
z1i&G<^giOn17JQ}XO-tom{g$AXl!q~%(^c#qAc5gpF@iQss&Y4T*zq6>Oq_!RCjhX
z*YYAtxGviumd{Y{gig!A>KLB)e0DKkWr89*FyT@N;!b~t=xG~X)kN*?`m?Pp$C;Qt
z-&a1_=mJB<Un^(5=YRNDmdeX`^>KMY&`^5hes1OBSqmw?KUJ>g#e~YNS6RCDEo@V#
zOc}WP$CwnOaemcTp+C0DV7PBuXHGTvv^+~%z+i^8!b=4tO??E#!hzU*`rNtU#>TZ_
zw?X&TnQ#L>F)g#XQ36L_?Ck0Ed+O;~AKRh7;(^i&7H`0t+7TGo%DclWf0Gq|CH<x=
z-5!t;!%w}-*qTZf$%?u8(f-VF)dK4JJC|h*gYL<<q=iy*JUENkDT6?#i3n;%8<vz*
z1Gxd7_6zAn>Az{-{Z{Q$usUv?Z;`2`sQluIhil)e(En23QExKv*IvR|)nb9vJy5-w
zy>##!p6y`l^r((kZ~H_=cHv+g67w)HOuuG*h(Q!}f<B{5Vn&lt{Ndrg@1Mco7eWS`
zKB%e3&PJ-C+Cyfzo-c8kuUsc1Wy`zSxgme1pbC8^pCZ%akG4*_NZ_CMPfp#%OX51G
zTS7h8BI*A9s1uJA6h5ok#3JN11#Xc!@0P^#0iGTeY01gLh8oc(VQV&RBT=s|91u|W
zNgwLuHflvr$6*rOI_^b5iRT}}DUD3A#%x4!%+`C*gK-jt*AH+zjnM-C(R4+@@&4eN
zRQJ1KlFQf*KWxaL2NqW{f&c5b?=r3rqwMWvpm;t$J_ZF5ox4tHJ(?(3?KhH>>w!A&
zKXAaJ;!!0$GHJ^Qp8Qr>v0Fu^&5B#JiEdHEmJZA=AyZS)UcoMze@O7{hj}mKIp&70
z2wCuCHSfJ5(Tv;Gym@oMY)J<W&dy!tw(tIQG~x`IT=O&-_wv6`N>QW;M*@Hk9C8~X
zEoM~R{9KNy5LDSQu#angpMe)FqB!?oZowjT`L{`Im~9{|e||FXeJF%@A(sm=BYX$F
zM|~C;$j}zhWFmGY;TGqas0mL`NK{}b&<A411o|GF&njbnxa*cCF9*IYEEHz|`CDQc
zLLQq=xrdE{SO?Q{<KNx5Vg28g$aSl?2HEr`IY^o`i}u4iIir45YwSVmxl^ZR=}wMi
zrW>Zx8BquA`~sRzM8WcCsk@B#dgtBVca!@9cN{MJ2C?9QzC|wL1~?>pt0Ea-4a+sF
zfIjW|E?7%MdIOM2MI<795c<5tUlrXAg5BD~izgsK<{XA9h*G>xWxyJ3=0)H%M3t%8
zZ|5LVdV4qME;C42$#?+y$SxIjp4~Y(NPEKLyLTILML^1BPdztB$V9V#F*$oj>BTpK
z{v#xIM(Ro@-vGPedsdqgjxp*U{rT-FXdMAMI=zgCs4mNsMMNBWDLyoBa&zIQd3h=D
zGtm9<_dPg1SYp9|8H3L-NJ;9rqg4f+N5s&;n(XfQINiMg6DarDW;Tx5YbM8nSBnT_
zCcI}{Ly$Xdq{kMm+o9#nq8S(Q`g(y(^dmnQjU2h17txk;iTRcx$cNHFA5d~V0mfJz
zOFkj+-}P1<s=ljeUj_NUGrYcIG%Sg3Yh1SM`ZIi@ge0ztl=_yAT~mH84A>o{9$Z9j
z(b5ZkA$XwJ%L-qYYQ~E%#Yqbvw+yfmFNfFgLG!kDPq<7$EN(vlnCR`4B9JZr#bcu>
z5V(#XDGVZ5HBk@O#;dcc@a_al1U0w$U^5?|2t3m^iW!B>`H?us#x7AU{>=}pv2L60
zCm#VHc~hd?A|X(7iut0v39(;jqjy5>S*hh0)rqlowzlF{&+(ONmJ#jHrWZA*8@Wwj
z#%M~`rP;8(w9+3;9B?^o`ud=3`Q5gi!#tMeON{`)lb;C~nLDtvxWR1d;ARiuKr$XD
z?)~FP?E~F!yS<Q^Q!&@X_s*@%7GW8ufbCNWNukBjYgCz?GB&*Ee`)gAu`$>3j%&#1
z>AQFG>ZaE-V*Xh#t-D6dl3+sdEysxpaT9YmZ&n%s$?O@p!qxapaY**i)3Zp_?EtCr
z2jC)?9^J`!MDnK;a7&3Ktkz*h%GyE;6O)aZ29uhYKbylmas~k|?5?g^7P(i3L41P{
za48{@C@O9>I`T34*(pcEF<0^??5%jl_5f||<3^4I`JL<5U77qm-eP5fv1+fKEke6~
z|8UNDPh@JNX@QXPYFyc5!kJ~NjDGPhLn&tdwSF%G+QpYQubCThr|j&ksXSipr1)Rc
zowfqT=KIK*BJ)~}Os@U$=6vCXu{^<NvV&MxzNp!$Q<#zU`)Hd8a-_EY)oKfftZm!1
zBSUnj{YC-zI`Y}6<Hs$a64=&>roE`)>8$D{U&%Ip>Bu{72Uw1cHi)JPCE~Bh4==(7
zWidOek=*J|Omwu;hZUu83v;)g9wA`KtD%R})`8{Krlk-uirNB=jU{s*okZ#ZswKq<
z#0<8Lq%p-8jvqjQ^edhAdZ(@zRytidkx8bQlvr3&n3Wu&{B*6rl1r2OMLpt8O!n89
zw+bg1exm2@_J(c?eD?1j0Vw@4yh7}CDM-N7A)DMvNlChSa}y1RW?R#3?Fa3ZrN{ue
z@Hb^d$yPqSs^gQWWbE?2F#X_sy5IY7x*4qt2r8%@D@}~5-=b>70_X^7pwst`aAnB?
zo<D7slIBzldHHBWx2_MQ>G<Id+VutHR?)34LF0x^)@tzSd4%23QSIQ2Ok{Z%{h(kS
zkSck@-Ma;8-ri7tlEkoyn<0G>7{w@Fk(fwuYIC9LN`vM3vlRcmDE2C{g;}F^J7Zyj
z?Px#9W`>Gvp`2O&!Sj3P=1-+dlj4D@kj;WU?Jrkzd2mq;8C?^A2l_wcMIo?r#MNh3
zHSSnsa<Lu12bR9fuq4jG-{+omoG_Yhj51iekN5Hk8!~>n*XvakD72bUD6LwtLLg~k
zzgWX*McCCajKWXn;;t`~O$&;cGhPAS67uR~F+`*1PW-lQLyyV7b~d^)qT*z|^>cEE
zeT^-$9RIWa;Zw?no_ixXKYh8RbODF>be?*7S~&J&;~Z^0Ib3Wn0T{@Whgl9v#m{^c
zTGN5wnpX7+1<s|`vb6t%o%5<&)5!q3i}AN?hoT*!O^=}*u&R3#c9ROZ8qD$wBGF)e
zI$t=D+(R?Z;!FnyP*5P~WBJ|bjI{8pC<QJMY8I8)VK6`1^a(b4NGN0s$87fqN$TsT
ztRN~I^O#!34Mr%oS8UkuEl~#y+>=7J{lMjGDMuhZplOlKN?U%)%mWZaB!VCowilQC
z(C>b^t)KOZH6iemt!HE@nil}>uSW^Xeb)55Fp;N92kHwBjMP@3P$>Vd4I3d|w`nIv
zU&Qb~A|#QyCj6=_Yg)5b;F)>M<wfyHX?W|BYDj1qTAC#Ir0~u<K?ZT=uF_Ywq3aOD
zgkHk@o1KQoKOykq(NV;l8^lBE{rfS_qai`4my|e}-;cNh7%PiRMb<)`7VL=j^z@8d
zO+5?5%LMw2tSEpCLov6R&GdKj-oAB38%ud|gJFd7PtP^r=pY6i0Bk7lHZiV)Pdht!
z#3<S@7)lfpSAj%iCkg4L3Q>{fif)gBup#N0#bd1)t3k%ow#>F}Ewf@Cyl~2)YY@u2
z%zcIiQ&w_NJuUt4^ozBto@!*O{zLs)4<+vaN8$shOyrQ+3@?i=0zUrSRtNX~DJDz;
zoz=~4>VPrY&dVRFtq9B~3y_3a!Ks2%J`#=?HL-L{!Tl3{WGm7hvG2f$?4Oo40@`A$
zK`YOUyMYOg0Be~#uo+;h$?lzXtMA*x5mKn13|CLx-H5_+^R{g>IFRYx3yB!eTE&a_
zkEBuD^BCr4Qx3eM*JL5}L5KpTg`Vll`3A@^eA446Z18SulykQ;%i<0nIU*zq@`&HA
zm_Bo#`BCpMXS!r{s^hN5$m|wk@kb2_i|P&WmM>HDSF=0S5md-dDGXL+CBptQ4K>at
zc6wwv#-?uR%fC1!mBm57ybm0(%XX_Dc;*fP1RNd^s4ZDV*ku&HonE#8-2Cl$EbG<U
zLeb<eErJ8#^6551CYVy*Mt4X2!RSNC8C$lPg}X4n=_3X{y)Q?k$Z~W78Lru401J@Y
zjUqdgcaPr8Jh;ECEGvwogXg01;u1S`bgZvd4c~IXmc>bQ(xgdJjF2wO)_HF82)B?$
z3jn11UtHk2if;jNZ$Gt)7za_`g%%r|WtxYOEvy<>FY-O7uQ~Eg=g=iyW(64QF_rUs
ze)-hVqZ4%6Jo#N`j2i`-A(R7ldUGMJp@NjrBInS7sQ`1jUi4W4fjfpr#l#%nywrW1
zpk**p7vUn|R$1zdHPJdBA4{Kg)|T0)^=mKH?YY;>%WLroGM?kC2P6Qo#3j-uQO=9>
zlXn8pIW{}i!bUIb*tJL%!jabE6DRg<vha<m?_zhqB=@!+3@v4scHNH;{0H?qI4z{s
zq)NBI7KS&VXG@JO<`Ev7LHn#r4YJ8VG_e#EW@Li}i&^J9_@J!nYctQH*``aHr>IKB
zk;gUhS%4=c)M@5hQ1o(h7Lnc891U~vGR>5!+Rs%$H|G-C`{_9I#1D8sR$eq!0bA{x
z06B5^jv&;kRg`tz<L>*pjhza9sir-wg0<)P_4Dov072q1K3K*mswHkS-ihUJZ*Pwu
z?*kWEI9L39YW~+01~iod$qF@7cJ*Qq#th0f(M=5VTSSPVoQ(8AR%GakY7zFs%>l7y
zpanqpVu(xU0dkxT6pg{<#U+>c^#6|Er1fenVhDZ_VKIJOzsZ*MT<j{>$iS6DB?Jkv
z&;Csnl)Ry(r3GW+;-Xo$)6VW5z9(GH$CyB>0ZYONQ)9tQ6%Sa99v!fI3R>JV>01j(
z2$vZnQvc74a+KXHcs)>TvuLh1oEE`dsT#1H6B@3V?$SVrsEcYo)PBT9n9mf#0tzw3
z_2YFu;ANhhcMd8QDU&ma6Ax^&&S0#dV8T!X*nSx?#aMkFWt@;K92|ynuqcFeAz4`e
zXwCC2NA-$H#Xg=MjKoAgE$3Cuh?9xkiJowA7h=^-hdv263mCPRF^A`_%A|rsqFiXP
zkcru^ZI6>i2!X~UWmur+VlaPkoZ=IR?-yZ+tMLZd3!xcB^;Y^EQgbkeoqBQnxaU~|
zP>7L#W9ZTq;&1FLiq#*~Z2b1$bF?>2-6LDn8{AuK>wTNeL0Vl7pYq=skv_Wdn#g)u
z<4pBw;fVC)j#K+55i$dLw7tkV<P(8xpMp$HI{xdJhQnW-HR>t_j?`#WP+WEmB9b(&
zKrjq-N)z@KkNW)`0Gm3jsT!=+Ff`<ji@OowUKCly3~-7lzz{2&GHn+Nq-sK4q1)(i
zT}9___yg6b*HTjawP8pO$A_5iSb#jvvS{_a6Z5|_t4?oS`ma71x#?jE6u9+C@#6f0
zYn3!eW>=|3;$We25Hnc=aqq~qL*Atqc!(nMrh-u3cSKOruxDYEug>`KN$pN<LWH%6
zhO<Sy?Yogm;X|n;B%*-e;6E#)8`6qM()lv70}q9&BIUy>rg4fn-RBnJ|Ho&%K4o%~
zf*3v%ULob2X(*yHo<p>_VA-+&UF8Gtu3?dY5{#zP?a{O6G$2rN@$lFE$t6+)lh=k~
z>Pn35i2$+br;xPn!XdtO|I6EhigoMOh1Q?SM?mc<R+Ez7m<5PZ4ulDNimOkaOfYZI
z_4({#n&M*6_CNhHbX930!5nFWLML5g;)gvNz@cxU`=lmLv#Y=rt?u(LA*^|Dgi^>)
z=;16jt=+^sXnL_jJvHtJE94H7s&K()(7qN#654>2WfcE76SZVi4-?)IPQPqyf`Y;O
z>#47Q^WHsgeqA--jG0*W4k`aEyV}v5S_B4GEh$HmBg6)|y@Xl{@vB^E!c{Q>@qW9$
z?NjPKH9jtm+F~0_RPYqzO3frX0&zu#9fHH|0#@ci&^>%_S*q1dhB$(Jll4OZ1GrkU
zCK6XWCT2&mkC5JnQcP?0i}VwBbtz=ji;MZKTX4N#x9wV@UpAX<sGTw(+Yu`Gmv!I=
z#3^0s^oU(bci?7;kvB6{nMg3;e3O$iE_=>y7Upr>lbFCtz9hIHUq$rh9six74lkzT
z;KA(~#)!Ejz7Wt{Xx*f^jzV6dGIiU#4<EMSKL{O79d<4cS=cj`m1XmB`Wegcl;#TT
zU>)fNU%VaLx8I&zx5@80j+XxT{${IT<3P@ajWfl@NEep}SrklE#20(B->o`D`lG<F
zg1{@tBI_`AfoPY$vI4f-J!n)Qosj7qInh!LP?$B1$@=;sW2|ny=TD#V>aKA>!;}u#
zU05uJ64%{+jVxXQddHi<P%LEJ3j2k)%SPc!$(^s4v#JZEwcE@Ew%*?ORc{GuD1;M@
zaulD!+~NGm{LLW2jFIpGVMdn}MlL9`h#s68x)6ZI5zU5yoBc&*oLq;NaK&l&<R;>(
zQLXgu;QwwYF+6;UP*&zAR#-QE)rV%3f>)qRx`rK5Q46C!PWbKA$*!Y)c-q3_OJ>{#
z`0c;H84P3Jj^cI7L48B7@n|;OnA-MYJH;+Gh)@=vuE7HZC+x^NFz7iVvtXvm?#d>R
zX>bZRk8$|@_-oC#3i}&hh^b1<&@43uj5kZX1H|>W{AlIb8anS9dplmxn%UBN?ASLT
zj@PH0Q!kF?(yE<1+?ezcP@|fGYd3r#G}@XnzPgf-x?3o=w;suY20B}XM^n=Wd1go6
z)isZ?PAvTZZ+1KQ8g;X8jV<XX9>JjI8lE2W9Po;((~v>vt{waUB%H1Diy5jvWs5qz
zW#Ob@F`68BQ!$}qbjgudX@~Hqc(|KTBlIZ(CI86v)5<H8b`V0PO2ZY4+PK-D2vX}h
zPh$)EeqHRinE?>tf+=<wV_K}g7HzZU<8Ny6h@^j^CQl9xK7YQz&#|*%lj0?2N{#`t
zj-#w=n>kuGM-MO2&>h3jYl%<EvGc1UHh*iCGB0v>yY5d<@wLFb)3*&X<QLIP_!cis
zF1$|M5Elx#RN%906dH=)NA=V7eI+ft^mk50AOMs_nKP6}^MhjQ7(hbs!|TFIB{+mp
zP7$)<F;1AV=Fj^b-``vOJ^($13zvRq#P{PrxZ*r4%^ChLk-rI%|Jt?W2H#nHH5_@n
znDL;j1p%QH9ZE)*@e!q;cKR6G_I{66M{c(J2||uCbz<w)bTh5jo=W&>{(7l@Y{QHr
zU->*@vzh+`>@3%*=?v<Pvd9y6y@Z-Z^PICI?C8;AsyN+A$4}YDsp%K^1_o|HVaeu5
zjE^FcM?RrYmoYFSsGo3{-mX3S|Izl|aXt5M|9>`}w(OORA}d=+b|Mt&RI-aQqG6=6
zHz^t_nGHoni$vL@2&Iy2DwT}PmVWo6`s~kn-LCKV_xt^E-LC6$Qt$Wc^&H3XSch7r
zmN)e9=g+h-8y#NtXIQP2dQ=)vY5^=3IOXDyF!g(B*OpXPCzIS8b`gM^bA>pB&hWQ#
zHgLz+C`#1j=4b^O&gsbR7JuUCF=PA(egS<F34#a*WCju(0Wr0m%(7re$MHhxXAPH(
z)a^g_W&DPYpm-MAVLS<z5n{lD!g!!)>(51o;9&<>`n7@{OWPwRKzJg_mq4z+pn+jJ
zWIzK=ntH_vzPm393Zy)Mu2;eMU=rJso)A}@rw+eyW?Fk>nYd<zRTCp51Udi%7~A9o
zzZptkds!drR>^3y0Sm?PBeFeI6$(Y4G_~>5zz$2f&-y>dAS6T_cYzvTXs)C8&*{9k
zBBANj-Wj?7cd-Xo=r$O{{g=51jT>uYdU|I6qcGrD(M6C2w2~6J2Tvr5JRpzbESCd6
z$25tx1(6dG0dh=|fT=fhqk6^P&3xR1p8-_EwU!MTA<<Z<>{u5kKik1*ItK+=?CQQ?
z()BA>Hd4<^vM>y_@Xn%BpfXjro~W-cDf;}^#!5;OlFwU~;mL3h?nC;9)qV5|f+B`-
zeYCglSRVolqA!$+S}gdidkJadHzvnw@^U%w_aSY77hIpe)W|Kv*nH3L#z>j6Q>Ko5
z{pe&nYnwkNZQlAwLIP{LyY}-5sbzNZL_xZhci8La1?iwSu#D4<iwg(2O=v$3K5`2=
z3cU37=ghX28EfpeU-N>!SX1i9DTjaciJq*X)y2eirpD>Yd;>H8f0!+y8UIMwzB46Z
zKXDKMVXOoFU0GYpimx9(!9HkFVL!fFGNEQuSjNl>h@C|$V`D)P^zS%@U{PUBwHje>
zd#<f3!+s~ih;=H7qG)GfkypL>(j`d*@l!fU_cJ4GPJ7PYZ9fd$ZaTFmHVkxChN~lg
z!h1UVN!X-wb3MO>4rR<E@#xAMx<3K=T3h-{L%ew`c(yhX7f%e1&bRnSaKZUOCPvM*
zY)igVVu+H7+Hv|5rxBG<((Yb!ll!%Rgz4@Z0wu&dRq4{DCVEb^+}gM%4&ieGh?=ov
z*1;1$@>vy}5~8EcV06XVx$5)cd*_-0(ftDzs&<9J76Qf*)h9Ms+21cN1$`dTyh>Nu
zxPMdsX|oE_E8SZjL)7(^aG$(INhkn^)CeR8PSiA_<&zQt$Vzc&qupbkgsCSvnI^{?
z^5^ui%ps8iSdy&{9JmII-X-@rGPHNepQ|L3N@Hs_^;iCoezWt3^p4SG7yZ^0=z%{d
z_-$-(jI!A}U|A(oxOwwV?Gs8{%QQRAkN1c-yjtGE?)R9p@{}(RUD##4=b}&B_O5Y%
zJ=4u)ip~pwd2Qvj<^T8>y)X9a7+hxTx+X-KYC-$=`c5YOe!PFwnIrA^w2`|{s%*0z
zUD%CPTK#GX)@}Jf*PKk-bqp^vhIe_qCWIqHQlwy+#mWzu#pD4k%A!C%BmJFDTK<~X
z%eUG3*UQ=ZPOm~Y@pI3er!y3BYEyuaQX$iDB<B=jQZ!`9t&XFw=Yo;+^HzNotgJqb
z{*g}_7E>9oAb$co)Mlz4f;2(zL2f3mUHi+#E9~cojFT%fHvh<{-XcF3VgChNCw?fA
zGt-JcpdO<Q21i2><;t3CQ8?HEcph!qLLw^3x&W(^PKGPIS?kt8(_$5$hCP4wjQOX%
zy66mB^=9k0c<wMlr!+)?1^*~LH^A#IRuo@aDXwGI{QVvoVd%-%aJJlF4M7_(;#@F`
zo;&x_+9vE(Xbs6)yvoadao5R|rE2gpif+{gb0V0&4#gRr24vb6b|A@_56Cu~$RBbz
z&nOL08Wmz}N%Wwq+3%Ex(>nM0G%##VR`Vj&&2=l*!HYhS5UvI-7DlVoejCoD?0X3A
zNZtu~T$^8AsZ$7GeRj2PyoeOcc&CV?^bX{GMBn(NwjjQRnt4cCYN|}Nv(|DA{~SG9
z(`)6&g&OXL%_A%;BN7aQb?2Ve9XaY-6d6SMJ+AC%RXze1hWG5A7*^Kr#fQZfWrjDL
z9ATsB_9{j|u!}SbKJG}ky&$_qRmfA1J}NG2_g}JF_=6^t5tLbAfYMi!?NA%)L966L
ze+3GPEug>1OUEG~0oi4&+n(96ePSh62ke&!dCw<5kx>#hdS9l$vQ=fADnS$3GVS5|
z^%?-H{G+Vmp=cB_N_KagqN{sAD;@R^@i)%2sc_+4zpl}jFis8+PL}ZyjVMOVSTfs^
zUvd10qdbFK)|oWvEvL3jL!P31=)WTU8SXUF(F5}7>?O<fcUg%*1fH#w)fQy;&Mopj
zbV#T+@oUm*3ot5v7D!rD0L{tD2mRB3)4wX~B&z6_)9#Qir9QVlAmV9moaW}^lL%AV
z^=%>R=7L?m#{h*5437efQJ}XvM-L&?0M=~4==qfO)^U4jLn&%x^eDZW3V{bV;;BCb
zD-)wFxlqFBqWBhnQ2Fnl@e13DbKkv_zc0;y*RJE*3`y*_^zKsvv4or6bNMHaLnMcs
zWhg{P6CVpxGmqwLTU-tiMqHNw6cXmZZm@XpS9vl%*X%^81otKdD~2@6^Mzp0{te$u
z>Tl!u!(q*bC!I!w@iSOc+xVE|NGPK>z`0EFh{=Ms6{lC@8Ov|%y|Mm{W7~*-W$_18
zqS})TV(}q?=P*<<-p$ySXmgZi;gCF|^Yf@^_j60|brcsb53VHf7on$A0P&W|uM=At
z%@_$hjLg(kD>32z(UDTZ0n3T2ipZnh--|1$`-arlWVP%=l1hWvPSaK=?>c49*~rM6
zlKGF!<N)Ro1TR37e>3oE$BigumHrK^&s{R<pSb%?4tI}n$(I*B*uYSe-mAR+oM^tn
z)bx4Nqha(%-!2J-PiZ3vs`T4~7D8VA86G55E9AtbU3I&>Xx4GFMkYKnm0{I5wK1?|
zUDjoSe69WUxf8-Px7Z|l`MdY-_4HgX1ADM7QP)dWvS6p+bj=T(a34>E;JffH%?C_)
zfC?29W>OCDp1SIW*bU`cf@^Tt=kQt3@Je8Cu7ibnK5IVF_tWE`gSJyz=(w3jYq9l*
zt^VMWl=x#4>={heXG8N9dV2Sp9{uD)gU6tm?w%tiqsi#h`dAga^0)7>o-zu>(8QOZ
z528cH*y-x&S#fkC<5M&}9a+|Bw@3)s;pZ5kgwckIk<_|QgQpp8J@BI`;74n~4CI|x
z)&T#C*^<KoziU@%TCQC?@$gE_8S|yH8qfG#<Zd3ldetiU%HU~Ul;nW9pVQ1g9ys#J
zXF0;@9{o11pKHE!ey9-hcq}QCKJEIs{9YWDAh3eOR>RQuhnS)B6$deSu~L1~<O4x;
zT0Yu|bUX^o>kQg;X<f7&JNIG^7?dxQZgcPZtv}}HH{;F_Q^Oi|U_4potrVy=c7ds|
zT)PqggzVtb%o1ca6DLhV=c=!{n(uS$bI-A>@L?XH<-F?^0^EX?_C{jj9zK7(yH{*v
zP9^~;F@;>{bYF*{TT&n|6+q73eaN=D9(yQcTTDgexw%o>COVf?U!2#7<>LeX%d8W~
zUvg9X0nv;_sEU*AGy2ZP9Xcct(gj#hoAs|kmJBdV-*tuWtYa!Hj@XD;S0|4jzslX(
zW$q1HZ4jjGvqw^a?Zy`j?<9%ZR=(!EjEhhr(_t*uSjPWLYIS!T0thZEHS8i~6BnqA
zkb+gr0lXDkKTzqNf*R`%Cf|GJKVt5k!6u8%%)Zb}As_2maQ7eZyW1qoXDFxd-0!tM
z?jLV%{G#RdQ@M6lbIemhR78%D)L~{e4vdFmArO3#nRShuHy_8}K*VOwdxCk{fd;z!
zaGl=!z-Ff5b!H6vRocrUOwoRi!^1NUZ7#b6(jdlM_V!}V5**~OLqbmn1pG)ERrB4a
zSs0+_amq;`5aD@Jv;Z%WoIrvc7^#e%L?r>Rc#PL+V4V3zt=G;T1x2IdPW2r+v^BIO
z5ki8s<Awoi-zBjp4Bi{vebvkD&z_yQ|Jc85mvW^bwNYEFs}9pHo!(}0CtGXy*5#3f
z(<&%-clY4r^eT`%VL|loU*l(WY{hAY`?n2|CnAv}X@hq}$a3>a0iA!iRR^1uE9Y@~
z3T$7MsM4sB=b$&3*Cp1FxH<qR4FWtB%?8+Gs-bp4R`3wLppann?nvvj6yO#S@i9W-
z4#(re^z_?LpBg6|dkh}O-`aZq{P}0w-~2b3-NYPLJuS8S(n(hr(h!Nzi!@1a2Fd9K
z(=uqG22L#GISm*{YqdguOH50I=}IgNebF7Lklh9AM`g_B>2nNw7MGdF(p(5+i3~v9
zx`npuZ?x<%CtJyn<d06mDM~~R1(#C!=U+#cg@WSMtX;bhEk}zU3$X>DsF5QCZzl3{
ziQ$1?5d92o4tdA3bbl&VWxeYn2J&A_F{iKa``6n>m4Pk$XE@OjirS1W((TEd$^w37
zGd5ujWKfIAyqD-a*i8|qFih_%P6nk=8N??`lXeP-lJlC-@zI(`sS7xJM5c@qZN~eS
zKe|rxIE$JQ7**&(v;?K_%G>(&tyR0WuzH9mxegYf-^C^)bpt}*1Yl$t9jb6MYpILX
zjX`AMK#y+(Q5L->WHw=ze?Y%W^f<)bN}P!n5q3n;q0N+(7SU1oTaMFjzR0E@=twTN
zB&b*bdq&U>Dse~(knXo^q~zFdVD$(O$I2F<>=oo0p@sZK9{59&q9CAg*!_W!Nd-F%
zG61&x)=is6?JB71y#_Y%33<7Rqe<qYNvQ~?i%y5Y*}c!6&F-M(aB5n6!pv*IZPAAv
zKY3CH`_iVO12OIag59N{{j{3@!nvCOkf9uPQP1JOu4}~2bDdgHdYGdQh4sK?YSyV^
z1L2jMZZ+=RQU$8U&N9SMrn<s~enF8V0zL>r3ZUbZErj3IMP0$y-c*`VliC5V@5AKe
zH@vB?x~aM+`Xy#BdT@qib)at&vu7bAc?&(v7Uf~?M?X?qd)&BfoHSVeRZSNH6N^}h
zYE8Uz+v~T!##+50CUC4nTrt+4j#pfruv24|zcl<`@Z<(-&|x%f(u8H($Zz5Q%#(MY
zAUwHISO=cOE?YFfddAyNo^ohVSSO@bekcTYg+Ov?dH`SB+RINdA>)PLfFR?U?)UGi
zt=(_-AmmlHJ<MSD_Yj|BxJr<%PyDUgOc_I{u3YU`pFKMaV;Mor(thjxyDEzSnc97+
zGrWW(qDr;MFY$tfo(CpdcEHqSbB#f*trX)ItydPzVIdKoYSVqht;_{4Ksx3%sjsNN
ztbqxdhM6WG)7LLD9>r&z`ToyYgBy8vnRz-PJZ5lar;|e-$S|W-t5=Jj3&lHK#3+D3
zcxq4eH3X@280l0WeU0(CZdI*zb=jzklMc(YODY%asdAR^Rb;*}9v6i>^)7SEDyDu3
zu<gy2$nw?M@+Mq(LQui+^X45pJm4d>)~7{&hGXLbB=6!SS5N%+@7fwXIJf(kMZSLh
z$&*9Wz`2L+Wpw((fr>o=;)Xis6?t&inTJbM2iV5vr1UDIXHnx#H-=3^`_Giz&HPN7
zTq*21MIJJ97rJR57cc==$ZNOp+alnhM%xLK_^+u0Up{|c8#oA$3slHhu5F1^qYMTp
z{OvpFeh-zoOEJ)L&PtOG&Q4C_n|=?pMLmJ4Uj|ET^Ru)v;2^LXBZ)MmO(DSX10$pQ
zZmOhIQ@Ph%Qm?XTM9}hxGEUAac0351UQBd_V~`lUV+p-BIx&xpUzBCwxok{fSp4q<
zZVvJ3gD(-~a|~(+AefP_SMJ@bPY41qtzxQ#1+dqN&cU`<pGFchLFmKpdvu|~gLR2!
z2GAFO8Qlx77!+CLQ7CQB=bct590-Wa1PrKeX`qA^ghqAG)dZfUR25zrdMZW5-x6G-
zPd~LS!JT~8x8>!I<&eh$Wk#ARaGXq&W4DWu5a?oAX0)FDcK*R)2qyxb_6ohRetl)R
z?oc{oXeZwtJL+&dCWkw3*aE35_AAi+XUbnpvzCHJNXW#}rTK-Hc@t!8)jwscscm$r
zIkQ7>MJpa|FtgaWQb)I`ak9I1^F2O2y0T`w)@~vL*|@&ZZWhd4HnZp)QfnUf&<(#!
zOIGZzIycTaxNRbWXnU6)O9|=aW<O(cev0M>t}U9)ZW$-24(?(*#=3#6)f&hShxn$_
z1`iQi%Z4En3__42w8xiXtA)*b@4UCfk(grC0e`d(+4F|Njr*(>6@{!qc)!mhGkhqE
z<*MaS8|Qr}BqRhm{H7T%Igp5F%Ob(o&AF(!Sl4Gy^K*kdw-YeJ>O#Fxn^POO7jMgf
zB(DAb$Ry?9Ts)Ip+5tidVmTlq1K{Uf@@pFIJImWRHRIEB_6Rpi;lzp8BH>W;wrwW?
z<oK1dAw|6z6L}f6+W&p@S;kqjw6Cl>kzP{Z-UcNWv-#gO{=?RI9Bk}iK71~?rG%Aq
z`IwlP$Z(W~yjp|h&nn56;0^?5{(l`~7Vfqxs7u0v=Dl}Q2g&GWNq$k;msYDv<Ay@L
zG1>m}<|%_S)GADmBMDrCuta14yZrslT)Sm+X0H11L?bAPGq`o7jM9H0OB?aH?$Jr%
zgVYm{0-TGCT!bG>P%BPA7Y~naz9SJVb5Snjj}e8g#E$}}DBTx*qbf1W6hE&%e3-qc
z_}K};$Y_tG^}snPRSLBl)o#>)CAEL?9A(lREIEr$P7FBV-nDGmymW*b$jn%0xd8Ym
zm9xoVQB3EMyGng5W8|n2ZajO|j=&O_yFJU}N!#LhCywh8l_ztZbt#32z>w*x1~JqQ
zRR1^mHj?v53ny$Y#|9M>M}Pp=ihC#ZKQc^HbHSoTBG-`2bJS)c3fQ=DV?QhJza7Oz
z@5BE&RV=I5|2kEyhuM8mbHG0TXQtSr)6-g<Ua9Z4DAK9_^PE2MrPm;aNR->yrQK58
z#^`qrEV4qKAV32N=6b>L$982P6~i7NrE4<919T2zp&%t4A~m+qXy9>GF+Ja9X~c;?
zO-z758@(IWiCTKfj2UjTjngP?COQjHBXk_nfQ_X&EgLu9NSqj=GEw`#UYd`574132
ztlw29UEST0BeVHXG`1%L1M6I&`4jyXTw@kjERUTL$>Z5*)ed1&;Q=G`fyDk~kWX?s
zfSwHGjrq!-Lv<SlpC2OOlr#{n`4Qp@0xBcck6yToyVvk_;RA+!M;*H|`(A5^s$JN$
zs6xBalG5lhx6LH@%WUvrsz)%@JEE;2WDHHeSqqg)Wc^ed2ir|sQ6bSSNb=b0Yqf;H
zYi<9vu#i&lRi;(Ed&v|?&^;kmKx=<J;^6DbS!b>>;^2|71gtOnry&P->!s=T*N{{O
zj!|p&5Kh(6^qH6u<#yqlGm>L3p-N~plYh!q`uA}LyVCxBoB{r#EG^alKG48mTIZAV
zI+_)%Eh_Z?rXEMdJG+QC-n4P!W7FDmQz~3ZN}3W{$^-h_M1%NeJ;#h4yY=v<;Y4V?
zf4>A+@03y4k;CcL6*KSp46snSY!v=;OmxqQP2R>ZhXWx;a?dIH{YF%_EY*M2{R{fL
z#=SQ^6K~E3Q->Z|G-VDF6-?$}kPS^tGF9$hziArS^G)Azd(&#=yZiPDZ8&c7y;`1w
zbMy04fGk8z#ppLWQxB80nq5tNnrGd2qFhY4|Lu~6Pw&v*)Ey^-gN@&>{U4*ans*OW
z|BocDK|2y9iR;4QYM16;-_Eeh1Dx7t?eYylKE}~i&O(#~1f%}V+5P5}&{JPZK^6kx
z$wex_2a1boS0$s&$|f@zT=*9|>&bbmqXW*mmD!gP;Q>mhm~rC&Bx`H;fJUBm%ruM{
ziy;XS4C|Xr<-4g=?@g^<$-567(qlppQ5VF^$@qkg^tm>~<U!*3o9SoWMd0wxW0FX%
z2=GucnZsGPBBGzRy}c#@Dcucf8hviLPHI{Sf8;CEum3ijQ!m53^q;wR30-a;Jm$w4
z8A!scx~}aT)vrGm;T*ht;(dj?PY|ZjNlIIaLt|pe{1>&x?aKj~m%-r@)j~`Jeycz3
zU#Vcnlp9}}a3SL&RUcN%&tx!I!v=t(`8Bu+UU}u_&26G>1JI>R9)hkPkSy7rn!--v
zUZhc`3_}ByEfzGI!gu(uiR^4cA5}S#z@@cV1%SirP!@PJOT!{`6yZ8-{gy=~T23Ve
zgLz1|sh6{y9D()bqrcs{eY<tR(}9ek3>@8!PGOknttw^!=*ZMcFtfx4s}uL2YZpin
z@8xzp=9DyVMwS;%J(o3sNrNbiAl^H%Q>fE0vnI)dii#N^9T|8RCtayYVy>XXsi#}Q
zyn}Dq@GE6*8g6{J`G1*KFoaPP8;Azu0+As<E4-fi5NzizfEu}r*7a1hU#z7@uSi4Y
z>=n;_<hNYzV5Z76!{~*<^DcsUIo7}evXX08?n(DO`&W$r|7R@0oHyEG!_}5VGA3lx
z;YY>PYV`go)WSdwGT4I4{=Xz!9rQY66k<FMV+8f6<Y>vQVkYJmo-V4k<6xZHPRc;L
zs)Ls*OWNCk=k2u|4pAjUz@V}cL;yazj2>Ue3YiWAgCQB@EWJ&o`@WKWQ?BZcGp;+-
z_%J-d^GUG9KUXow0f`iiyy3g#fD>w`^<syh9{N9tyz05?)25zHwAX>+ivyjic{nN@
z6j2K>t3nsT+jdh`-2qT?{KN^Bu02G;kGOjw(+{LU;@J0CA6r%IUz#yA;`<J5i}CqC
z=f8AnMj)|_aEJnPRzw@m?tvkXe&*!*M(zHkGV_tlvx8$lGu!aQ3CRcKmO_T_an5L_
zCp+RZ<HjNLc0b!O-L-D!lC0yEZesO+jA28%Iw5ICt4z4L#uUKb11wHVYka(})sKis
zCnPCH`8Fc_U$D46NbI&sJzo#&EycGtVlUxl>TOhSHZK%`{O|Y<V=H&{sY@`%o7L{e
zInq=sMp;RoIRpq-l1vMQUU!?+-##a)y&y`6{q}(i5<3da)O?mFB|OGPF4~&(0ciNU
z`mA2Hfzq%BsgOG%Bp=~}LfPV{m(7G4B919q#PZ9ba5pIl(|CKHS7~YK`)4uzIiKIM
zD;p6L>@vKel>tmTi^Ge_C6Kb+SU^)o8=al%?-hIS;6a+X?#W7_ODgOzfRthyrdL4w
zQD{)3CY+*-5Tha?C0YhS^_&rKX7zWrcWzulTs-=E07P;%JJEWuw6%M0ar+Qcb;2oa
ztJ|f=#^eu~6rzH#H8+1rhOqnQL%)8l9klF;<lBD!_N`{&PsU~pQ2<cB$wEYc)sV(~
zo57~)lBY_fAk8P6Kx!LI*G<c5RK$nP&y-UMSFg+s`d#v}yt-0eAj}-62-wn2q4ox^
zs9)M=k`Y>6!L50VU6Xc0iHfKQeX;O+fKgJAi*c6fJ0`rVS8StpL#|X>Zx_1;tQ?nz
zWU?-*>#KlJ)K&mkx6$KyX)GMS>(c|o<ub4j8i;oIUy@#|KUo?zLQVU^l^Cd|OvE~W
z&iKdd%5`3M_nVWM%gQu9#}#C91HI;$V1$JN>?#*j0+_e|+(1xMnJGdYbYO=xr<Kgy
zY96+l(a~iS_tN)XYrCnO%Rq#T2)D4sWQeu)_+0(68Ae6~3XJ;*gw+N%@_)_D>Bblz
zh#59~_+j4vXNcJv+w@+CE1m6{N>REU;*=U+JMQd5-b8t6&PaskDNr2?GI3bi;Ub~I
zdB=z6PN{?DfUCC4uG%kCLtl`XVv*uN^CE;UQvnTpo1e=ysr0dAjjGwS`IQ~>UJA8@
z@eritGbO9U=uQk>L%|7DDQ@_zP`QjC;S#et$gzP(2zS&4`|rVS){$pQT43Vt<{1)n
z%yd1Jc*Str!DRTxG<fn?rrEpCOuf6$hJmX{C=nIQzmjm%&J1l|SmPQiRb(*S&$y`$
z9lrj?v>-2Qe($O-#;(bxv9&&TdUBqA!kHA<Z;UJHD8v02x<*Kd*ffbN41O4;m~i*S
zHu%A}Xm#N**p^pFD??`#vngCf$!wp8#@|h{UVmYdZBcOGOxo^4*Cw6r+^0{YmMuM1
zreDSt*|A2AEh<N!BeW7@tw74i!X$m4MFq>$$>?_M)6~T4vwMp&Wz(@dmFl|`UpZ!;
zhd)X{X2A@-Mc~}>4=8qsw46Xygx+ES=MG5vF@OJBS15+%<UogFo&ENFSC&VoG234i
z6!dC836SCArUM5Ij*qgMRr{&}Xtul0e1!|^zIG!oNAh0p+|dEi|7=)bbVF&*UyY01
zGawKoIE8mE!z%dAi4JqCcFOMtW0m!*DMebfZQXhm5kD>Z%&A}cAZ`SirAW0Qk>634
zP`K#kr~dKuJVfJUYwLbgmh+G^%G@4OSeh1O64NA}d%#N#Wa-dE;vzuDDwCu7#Qoa*
zS2-b`i6fRgyP(0E1>Ea^0D;bGERCOSBMk1H(jRbK;k1+-#uyI5T_tsNWuOH`O?=cN
z<L&=K*$LX|b#0P_bPK%5*)4v<6))rN(|F0Oyj>-Yn5FzVt*p;fD$G6X@5l!eDmKZc
zW6CN^r`MW?BZNzc8dLZLAT)}q(QJ*Oz-SPd$lhHTP_?mI4RSU-BCLEEBS#Y1Uul76
zpKuf^Qxd<qLr|&_v7|C=m=DxkRXPf$pA-BIv`51Cv#qY9lkpo>D5AHuUrx-BfMjeU
zozXu7jCt5MLd!A+OK~eQ3?Q1b0*^W^z^AB?ylnDSrx);pJQ~W~2GVT8v%koDaXKjI
zvQ6V^<^8vzlx>L>fx~qIh3Kp}hnQ<~H|ZEEDA*jDICj(wyDD2QYZ`c0QXR>9bUfIo
z)6R{h_n*|7-lB@!R~maLWTbYFJsB4VyhvNt>(_<G(T@_w{5Mg~{=<zlqDvazOWRE@
zT$Ql5yrGKADP`UMCLPgioE&K4X&&WK@O>xAf)L@)?xitsl&Ftr9g8FN8Hw_AS%ZIK
zu%O!D>%5VDRR0V#2k%+O!NI|=5Ee_uI#Znn-1t$|ReSIB*K4i~xGGTv^w4I2;({?X
zYu4F+t|MSFh0NYI19$UnWi~CMm#gRs@tG|mn+bcB516-@<DufXLHW-bm+ZeQlHeh&
z0uZcgIsu6OKo=~2QjZ#=@VEi3Bzc%3Wx@0!o>Vf-&?@YKz~*jLMN!D{BvDT>{(68B
zBJPn;e>vyD$S>Xaolcl3lC#&0|J_{c52@l}kUjzz@XLk8m%c2<Dfsm12pBnJU)O1?
z;d2)7e^S!S!vMj4pnbf~6aiMkM4$9MW3uNxft14)=TFiCvRwLmN*{4J$bFv7L&VA|
z(<#ul@Z%&88Zh|=S1nMb3`UoP_^`04OO~7(U7?tfRC9)HP&P~KJReT7u`r}J%`Arp
z`|<I4B539>Vn@-TOV%AtPK}~XH$aWQ6c(Of)nWuI#ITf%nMb%1pduNZLsfJkHdY)o
zGRy%X-!?=U+}!ga;Y1(I0Wh6A5X$r_Z(24E-w;#PYXa10!6q$RYOymn`@gJ2wZ!CZ
zu2DhNPu(-m2TAX4+eliw`O&{O-b(|-m#b8g7TVDAEaK$AzO<i1TlOPenkw662aE+E
zu^cP@FDgwtHH9Xfp}@SHdugBNdxd=e_6;j$7m7an4&iJ1G1{=$ncQN~0wF(WEt<DJ
zRi&idNWDhvVha=>MU8GQa|Fgd?CUG}Z|J=t1zZjuyiSr|R>E_zG3h1+#Z1?#Y^y5d
zmDL#uG(UQKqr_#GnLUKz6tS;|^WEf+3Du8sN%li%4mkbmL&Ss6g@xCc!iNO#(%0`*
z_E4=G7q_hepsWK)prkqH;WClP(G<)0hu@2%fAivSC_#Dd;fZ4?(iNa=T|^XuMbOsL
zpYi1)l9S{vSW_kkM;Y8tW6gG@AFWh?APCyYUj}Ow6DM+;HzdtqkN2Cb|4DaL#CLjI
zLd>=t&M3a`l%SP(FD*Q4l$G_DH{<9-W__?TGtb9Va@nqNwIcI;7L9nCAkc&tevz>3
zGI?GiU6Vfnqs4sx3P{i2JLLMcYgmL#Vrn*ViGP=e@s0EH0Q2P=jVx7O{>x*81n-I7
z42cwkkl1M<emoNY{#1mr?8zW+9FwDOzf4^=V#z~g+*i8?n5<vBR^crC658c>_1%X;
z{`m2gCGGI@`5GBKJ~qM*lw{Jg&#Z)T{YjgVIkqr7z@RGKx@`xhAP?b|IH#sekz^*>
zO$7eZ)5!EBu9k)9&az%~sC>U2N2-+N5BnTYR`gQ&AA_<x)ksQ^eh7aX_x<@BBU*Iq
zK}RD+HLghAS@BxtV|C;H%hE>~+3$1Q%~e*NTd40u0WKji_wVajE?m2I?JkccoCAzs
z*)yUA`b?Dg^zT<;`{20RKv^+h^2EatGb0=Fx1?mCn0b#*0fQeX=w8rO0tt4*qM!#O
z*Klg_6z;d6#4x4i7ejCeaY!tHkD>KKOZ^Js$-qktYs|O6u-13bpj(82;;V8Ca*m7~
zaCfe__h~&RUEUx5_#B7iV*G65%#*EGu9SF9Sh`8qE^!W96E;r~tkJhGrJdn{`sRxl
zgRxFRum7zKSOmoWE)Aaq4l_W~dv+${bFcvRITupJZ1l!g0>*n40tR}dS^M^6IaR0T
z5+5lGP{y4hDq_Y1gC{*OBsAu4fEaKI-vYj;O=F)Zuu)EeV3jfkge@eYAy}Mrmrvj?
zBCwUQ*K#0AM?yglHwfq@upKg=1@ZAfd;}SYV-GNwa>DJ;IZaqi6Ua0IN01q!5~C-+
z(PuFy&t_b_ps9!syM-v|&~r+f=U);I=N+kv#nCQ}7Un!Sa*04dGqGoO3?P?;;W#)9
zhwqT1o;FMQW&Mx;)plna^gr0{797j@f02`U=1IN`gT&nhHPR4af=tll#!N0k57-y`
z-L_A$RRX+m?nzI-v3UC>sI*YuO$k{YViZTpLxvo4*iiMN%qmOsv2!PkGR|QrU24rj
z-v*Qi*&GRwGVZ^gBRti~2;3d~mV1msw7QH&CYWK9!}-x*VZ52-TVGkK2aX(>g1m&j
z-S9%$?z+$Mr}n5df|^2%!hZh#8XN{3E<64{jKuNp!$@?393}-X<a&_790xK_fWe5J
zp7zy-lbypEx(AIXKRSRbUwp&}c^Q$j5mT_+6hnx6-3`Ow59xpykK>XzaPZ(h8VV%<
zq5fSIU}<wGUb1k>Ca;?{zE9O9aN<<*rW-qyowtPVy1Dz>zYX=c^nKo0K7@gSf=+7}
znJ?|-l`$+85WZ8brnO3Xo76T(ykIm{#GrNSs?FFi@u!k*%Zu*a{MLWXz~j<}3Y^Jj
zU1~M;ub0c5R_Ei#=O2$=OkV<`!eyx1zCR;S&_O2W005oEpTj4Y@|ZcIuejAcl3F@U
zSoBGc2j|ZTVR_R$zPjJyX=e+dxOzli`kO)|*jD*Vr=4$i$4;4L-t<Lj+~mUnM8H1$
z`A2B3r~bok4ay@rs*4ZpQukfzy8+r;uG_ymHgLD%^MoFL2P=$dTWx{BtfQB=2G2uY
zgD6b7{lVvZD70i>qryXtaRoeqSd-Bir(Rr&*Y=wHxZ~ULwpAx>L(T%ix-S&I`TKN<
zyWdK?LC{<KSaPt>IdzXq1~<sL0lz$Ytt-kq9i}89i7v}eXxZf{QG_3GM)GU0qT8tP
zyngk`?*snbEye@<Pq&zE?_+Kn2t~k(q#lyckcLYt@8-I{8w7u=>wj!WQswB}aNz7$
z8{S;tvSvuT%+KLTs16t~!?@YpX{XX4(x4NCr{iItgfk@41ftOR%#hGal3ycsKNNr>
zu3#ZeimSJgNm(!!JsP|R)%=fe$drDGUr=-vQGt1(IN~fDL&sQQkt1`J9lH%hFhSc6
z%tM4CWn{sOZX2$10lgSH@FNu4*@%eiw{J@=^&1N<mH96o89-UYXgjpILc;LxJCEP{
z3b8KC+*j0{-h-{?eE3Na$;h3L<E-KaS2YQ>f|56F#p#S5=Qg>;C^wEFt*74Suy{k2
zZBU#HhS9i56Kd=Rio4#@(_Nt_dqT=CFgAzz>-X=uZW~I+wqr+2b!YWH9ERwOMO-Z?
zP^BWHw{J(r`=YPBmY&}7FVZ8SVE-dMa!$bN%X;n6NX|n{AzDxf2qHbzNo?V!+J7y*
z*Zxr#h}HQE4EO*^(TG?0ubr5Nj2(i=h+ObQ0InXZX6cWs*(AQ~M_ZTp!&CKNI9OHn
z=!z;^Z95J{W{))7Gk;zmph?j{knFhOvU74VNLH08tHk7dNRL7aaX_7&9v+5XKVsbK
zjBYw(U1g?rg6_=RrBy>FnTdDG4ItYE1|9$6?p`)jf_JYgXWIT|0_f62>O11e$Hk;V
zf!omxm52S^{w%hM2@N}H?WI4WWfMXOU{r7<7&F>x&bdiuFNYg?yG!&vR?FSA{~U(Q
zus2+?QUYlKQN^c9f;H2IcERu1&`7`9;PDo@yacvVS<n$sJwk3><Fbyi%WnahVV$vu
zHJ|%3ek8v|=D5*fk(AMA*LxsZ8br^CPVpA^R+AS3gu)k)d0aGhU2GyKe<V~0$QWIy
zLeT<x?qL#@2dpOoMIJzp=uhnUe+^{xcWOBnD>RoAVbD5=SEL5Qs^X?j%o1N{-y&xQ
zOlVLeGoMbfj{XDO9e4kknZ}9uqL1AdWZ`M)I%LR&8_`u=>cySfZ`xl#n97j1c?3)W
zQ|u7LncJHT(Gx4%`_Bp@9Y`{#C><99QEp3Kzv5|R(8GSm{;R$cBuqDSHb)^8DaFZW
zyi+p&+0d|sDCNcBK(Q)`8rr{WXUn)ibMspu4l*?bO&kiDW-VK)PRx@AkUPg~$f^ad
ziQX~@20%j8;{0p+qefUml}A2AE`h4yFwcenJ8^{w{0=&nO@Q7phAJ@B=Gc>xAix`P
zO@;#Dl4Zofkqib!dq*(d;;e+?qN4ezp5gyF8I)Pols|XAp9e+y$6&fHn|xHH^L$sH
z8T<9Z;pFoDZ~J5_Z&OL!`lwa-%+cX}ZtfggU++XWce7iIUheCf_{99-=72LAtM6)!
zpS4}1+3P){RMwC0Kjx%H_|cagM|}L6zal2~WZ&Z9Oc;G>m7|q&@j=dE6PwVI!}<38
zaZtkw2y`X+T)fu39Y$zomenac7&CWZ6H}uegRjua@VwGu!baEav{mhb;<tJEMwB2o
z5PqyJFZ;<9C=pY;xHKk9S#qepTaGd65w#t0andZOe&LakH;~RZ=z}rwB=<D&mrFx(
z3JO93hOc@5a1)g>Gq4Bfdi0!#`-MjA4LXp#^DhO>eDGlE^Eem-p+D*Kf>R<q)Qx&i
ze=*9Q&$*C-G4F9C)uBYV>%{s@JM*W8uAAB>axuVXRT=xE*t`e$)_ClJ1U4N{TB+5b
z(##|o>Kyzs(~hDFGBPZwO%~ELssRO2G4j$S!Uk7E@OLNRR_&+j43xGBa)J~!YL4l0
z>R2pFyCI@nS}5my`t(3%8B?y?HVjTv^(vX!?2(<nbq&h}v5k3TV-5W}e^I3R6*sv2
zcywNZ5ds<jM(mi}x@N{Bcij+IpD8u9`2+&}zjXN80L1bw6)=YAnd;43M^5)|P`|#~
z+_+2LF7+*{S$N-GiTq}jwRQ5-IX0tkBOf(O8e^E?*(c21%2lhL=E;6$39p!r&Y}kD
z@FQ&lsmS;S$9+he0h6AV-jTIx_$!k#?FpJ+Fiun=wOHo-%D}iI)5D{*zGu5Fb42Aq
ze9xJ<&~-C<A{5~Wjx*@@^K`cp`A^q$+S+*Z&ciwr-ZXcl6qJ`Fjy%dy8L3Ah>gROO
z_ei&lp(7j(f^Z}pIqm4pZ$}1o6PFB8xg=oAtN=u1$we<N8n{MyKbsU0mQgFf%>9sW
z=7214z1JT<h6Ze-WbmciX^PaBI}yRBetN3yG&;Fi$h!D>{_HOCDl#f`a`&e(deKS2
zFAg6FL9>=iSsGx+UC24?<iF^nk>1$!s86zv8xM7LzM(EtR5;@nApLgu^?C=rswDi0
z0Rr=1y<_gmj#N66m%kh2uBj@jLMnN>q=)1**cEYZ_3hhtZP1`j%U>06o>SZyc;38q
zt9p6){b;RS88NHS;)$?{Zb^*JJnC#fCNLk)986p8Y3*xo<nSj7gLtpbsHbqRefEE0
za@5|&097U-<iU11%JkG+B~W|2u~El$wfRFH`@6xpI+v=mnuU)&x8Nq@AVldSAO(g0
zbeK8f!|OI^U<U9Y)*`BhMV6fdXXJTis3Kscf)!=4=+P-`Y1Tv!=eZ)C>x304RhW1P
zxEsX2%M+O1=gjws_mU<C8TiZeT>3YHmt;n$pnw!2YO^o&#ozA_2rZ9s){42IvxlP3
zKV@@x{G3#ugV>YgprKx1#lGR6iw(5L%;5L!Hn_CB`)u87D8L)I!wvj(FXx&z;r-k&
z(J^0cU(37NT^Z`kIVu4gD&uxHrp0u1ZNkC+mNQl?;*6pIa`Xw>_buo#S|%@pAe+-f
zvtWKD^L~FNwhhlE$&RA%u(ZsZ6qSiZL6UO`_ZF)O*;N#55_NCq%eik5Fu65n;+L;q
zB{@^Gf5-4Q+1WBY0YK89AVG8&@@gf6nci3KX$sG29cv_<8oR4$*t1;<WqJ3-L?ou_
z9z7JXLb0HHvy{%YzO1V%nQ_O^7l;svqaXRxHqRBO0f1zl4x~uDZChEMYu8K+|K8TE
zW6<MIDnq9fd!a*-)E4e|c1+=m^`E}*^?P<anmmD<1ek=fk3i<1$t7JaPJVLUY@n(W
z@+o+;!O~Gd&HU0zmG7pF_M1K}Idr;#LEpiH13?Ad)QuW;?tIeo<JgV$FSU?gxgy#1
zPMw&EvA+@ieV-D`&KXPqHvpX^>4LApp*kC0v}H7>N6EKfi*!otKr{uj0!(w<exI2b
zon)DD+Rv0Q7YUU@#DU8)>4$^T*2tw)pQLC>ycit}w{%|u*^r8E{4hP4#mJJ7@Jn`z
z20$Jt%r#C@@-!5#q@+x58oG@$)OD9_m%=|+B!}`o?z7(d^?J~|;3DlRFm(-`*m<Vt
zoW#UT&0u*kGW(jwNh7^j5U+tCdJp;)Xa;`EIecl^)9>8(lC{VuGiS$VM9*!U9J*!m
z=J$_-n!yfp<JN53)@SnaMUyA)-@iXcysUsR?At;d>k$O5iE@#2Fet}^PoulcmaVAL
z*(<91{;V}m?MUO@6geu2$CAE2zOaAgZ`FBf_rlNAQ%!#}Vbi&XoAhwhwTC(0rr2Dx
zB8Z%h%Kz~C#qi;(GL90lT5{pgMcLhCn=k6pe%J7B7U>68mvu`CwK?$HCWW#a-03~&
z>CE66$3fd*x#b02&TPg@9DB8E`&|yo@-KW%+ZOq*_C5IRs1NXEGaO{(woy~mm3do8
zrlGybias+tN?nfe%@c0vygLVC^_8!BdSW`tAW1zHf<13sk&kZdk$z^1Xcq!0{kb}K
zP!V2AzBk<aTh6yR6P|v@E~aJ_+KxxnjYLn*YRSfgujFC9-O@;F+6J61rvprDNE#%F
z5WSUqP&3zNj(PVdG6V8HM#nXWn0!T0W*?qKs=c1gc|U%WgnWnr=z61(3?OmOpE7p5
zSZb-7sNwn%N{H9EH7yM_SZ$ZF%jJ>1@3Mxa;^c3NOu>y6q7Pu}`84p7PHYFp%8|tt
zSiGLbqau|B69wf;AWc=+;nlu}51(l`xi(JC<Hb6jex~^igG+cf(&<BA-6r1@i`~)@
z4L$WaZzZA!502<-sp93NYxsCj-@Xd3P^AR`(}z7<RdI^Nj{C@CE!B;sjOj-Yx*^Ch
zAuKYVWhrB&@$w;-wK(EuDo#(R(x7<8lpp3sGt-ToGI=t|Xfu;TQzjA&!~KG!eINg8
zA=M*?c7$m>#gw>rSa2z*YNh{twWX1GXI#>D)sU1g2HV-Et5v+-Q3pa^_RH`evcK(M
zXYL%Fer4N#^!%zNu_eTh!|@jujDY-<tWcWf4Y`Bxh1`dTXHr8WdY06oAKxy|;uu7|
z&26<XdW|ik%^vW(0pIkFTng+qY4m{*8^dV_X8xh;s~i<~T2VKomj4tN<F8w~n8f>2
ztfbbjdH<~{N1V~zk<|C}B?}So3v|epDsl@k=mR>*G+oXK?Wa!^A-=^)jYt621-Y+&
zPDzf^I}d74&|3>gR7fopM{0>0SaRnm!^W~9f=c}M^WtBVb%irpMgl&6ZrZ-tfpbY<
zf?Pp3v1W`ZkzWR#bEyB~hCI#d&}=mJ=4}QXIZ`uuqOz|PZiPo|yUY>I89;4!ljxox
zEz(U5(bVjR`nmV)3s<--B(fVGL-Z~9WX?L3*~2E^<DQSYc1r=b;wX*<S)%CgUIEhE
z=BMfDU6@kdtW~Q+3tci<2&sFLBou`t6S^zx4EGCF%8;?o2%b@oa?I|iwM_JY6W)#`
zA2sfLwv^aPX)zU*r~A?&0xe7rGU)2uZs=(KTQ!jk5`!>U+HH(kFcrBDmvpM<ChJsv
zs{{3;o%B#K!qQ8Mr{#ro-oA*oMezr}dW~nnia(u+mU$mL3(>V(_hlb=V3NAR;(mn3
zkWTY9FCTTry>IWQ5Hh~*^Q%os%ICQvT?y2{B=tCGGF~0Ay@^woQvS3aR@vQ3-8W-s
zOB!`8*S(jC2cU5>N)F{-N?~+BmQzL>+O=ubYMP%;laQaF(hDHmmDCO4EiI+yf+%-;
zTQW)6w`OuZIeI@)dk(~^a<$4JL68Gd;!&JCE*`zO{ikv#L`Ku3EsQQ`fEWRw-<zTa
zUc4F7(s7jIYSRPiQ#8!l?wzY>Jq(o@ox^RA_IyX&M<NC}(yj)W5G}dvc%)&kQ3l9D
zyuaX~5!+YI@XVp&^~F~P*Yiu!tDehNtLth+x$j*{_$g@-fwbQ9tgNQeQShkzSeDv9
zs;$TXHED#F!BWkH&Xu5-PW}2d9X$Aa&oTFHYsFk%`=vTPF#Yg>+{*(}HpT@DQp}YJ
zYi2>To#5g0P^N16W75B!YpN6IQ}sB)<Z(P2o*oZI`90J2{;MV9^nt0y2Pj{pIXy?l
zAo3Z%<_%Xf)fZ#26mG1@I`Gnx{ld<(K`M<Kbut8G)YFUBS&C?fr8Jh>OYmK~bUfcO
z>YK}&<ER0*_jgwhq2S;-+L2}cEat0v$1S9Oqmm>qD*j?mO-<twwYlyRls0>0PK&h8
zO0al7U*WO#MG;8jC<O|iYgs;Uldbp4VQZtbHTNAl)QVHxOVh3geUevFd%s%AQCK$d
z>KaEc^HQC^iW}e!xPindS*kt9qR9-c`7i-ZbyVf~`^w{I_v~WhI{kWGhqWU?{g162
z0WUYRiNsmR$;eLJ$BxEGwE$nvrpVapq6$ST=f`JkH+-!N%T~sdqq5tzbLTNi$_y=!
z1Jhl62u$I2WFG5QaJ_{~mfYcb6+dz-P1_|$+HIkMvcV-zk-LLJm9x|+u!m#eyLyOe
z(t}Y}1`~KHmxh%0MjoRL6?K(OSLC+UX~~49O}0{q-SNBf;HeweQPPxyM|rB^!-w#8
z;5LM;dx&6<VFN=E7s;S7u{ZHyL9kza`m`Ui52fl*mq8l`14HqLD|y#UpOOL{S0+`i
zjB<b$40alG#1)ZVlJa0)B2RA%%oT?$iF^lfMar=DpX02jfQyVp)tQUO7X0@O&=HZ_
zEwwMVJs6k7U(@>iYaz{5E)WsW<%96&tTVR%fr642ZrT@lx;F4vXU?2KsNIqNAXQi8
zfm)#UMIKlR<JI88)&KsD>m={PILKeRoObLyYk+rx`y?sF%Bxq;o+86$ncj&QRQ?Ai
z&jeyp{wTdSn$URtz-^oWB6iE0{AZueR0hyaMv66R*7IBMspO_P%F@xOxtnptos_-f
zS<U3;zb5!7t{s`@d#rVet1k-!Z}d*=*D%*%7GZ@+{CFvnP*I4VG$WL0iH<VZaf+Eq
z_@cW;_H&EQOPNvE^u?|TKHnzp{SCH6bD89MV+k$o=rLnjb0L6<aj`bT%ucPx?)9U@
z;MJY-YS4P!+O_D6Cv!6#|H$GwmGno97-~5#@K23_5{n8Lp8C-J+A{%-?j1TF+O~P~
zZK%6|v$kAZ#xlsevcPoLeI_N&s{Pu(oJ0HudEm@`?0^6rst`Y=VI7k(#-C?lp=gb5
z50+>VzFGy+niU~m<UaNFZBHo&LNY7=SHA8X1bE$ugG83|x}ZRhPfS8#y0I!F(>ZWY
zl{1&e5svpNw9#WbY4}h-!`xh<X6G^>u<XU`s4vXyf-4D}a+z!o?}f*X@`>q<q<@lA
zP~3Rx^-4Hm@^aR2pzv@`XO0^?R>30ZHThzq!bGwQeK;O8m99v}5nuws6>$v-`l%y(
z_6EI?ozXbAEN58L;%?&yqs3$n%H?J!&o9fk#_cEze6CZGnRAIq;yJ|balXiy5Sc^|
z$w;jvW4D3e@IxoAE<sc_f6*d@N;SEH#Uq#zS`I#sq8j}>aKb?P$FqcHhS*u_&R>xp
z+Mbal5f^{6<Gar|)tEacFC03T5YJ=3kC-k17s?_8;&IW*)_+KJ{KF8F!N5D?@p1lw
z*kS;NUvUTTAN<jFT!&nXS7C!u7lt#XSmwHcLa_I|G;3st2@<OO!_%le`?ZR9;^~t8
zE>oXbn1P``;VN*D+ViZXRO&t}ybI+1^kKFFCK6adKPCW%z`P(O#EmA$?gJP2N=wI}
zke6b(kj@@Q=Mcnh(Is<{PDvoVvvUAXNQQ}sJ)TCv21jWRqtG)>PO6g+9dp-reZd7F
zY^+K2vf~7m@OV}Nm9yS6=o4w!%n|%Oqj=1mv8rN!>?<!lsmGhz&o~a9ShW;Yji)p`
zG(lfzFl=a_L6Kd%YiM5Pq41uoZzR!-v_mw5?O+I$m(R<miwJ-I0=!jP@>A0~$@mx8
zYj6@G{zs+^I4tIP?(hXHbRvuzY@`wmB5?iCwPoD6nB+y4&IZq>Ccky{>ZpPW^A*bR
z;Fl}5e7uqUEyXKOpjkFY4Zkd7F^N)$Ez!HHi4w+c`!OhQ_|mJ?z#AjK4o2Ne&v6SZ
z^l`g}j-<GW-%jp_?+eN)*YbV|LP_8|v(oJpB(8?#kqxZzj`O&arlvRWC?1MGHqscA
zSOb8_do5{~siUW7Moo!!!}4+mB4p|AAFqy>9%F5`y<z(VR4ej$(d!aOcaUD?^wF2!
zQhu7x0HI*1roObI+yRt1WgOLm$7K#XBB15Ov|0YUD{!JErR<k5b&ZSQ3>n?V*D!9G
z?7cW;V9O$xK{nG??;li+pcf0fR&<nvrgk1WbZE-9`2Zbe32u)p<2ewFw^-Wf&If7j
z4}$bgnj4l0uXzvu>k$rw-=$xt(*5Z0r61=Mj9RlGA`UTmq|^Cx=N?_`ZvYAuVlh5K
za|2ZuQ>k`>0-ERPED7kHDiaVnwBm|OC;|VBcN!rgQ}&%@;P}pt`@GB67JmyWUTXqL
z5t(*ADr)B9p$S0^?w^@XlAUq>NYrMa#5G>Mdv^nQNNPGa+>&P(&K0j`eQ@ijvJ=n@
zFEulM*Ja^iLcxBEErFjd$h)MguU_q8F-L%f<DTUX6W%P>*_-sy(Yo1t_f_ll7Fg4U
zhc7ewYQK8<`-9gG|Nhbq4xLNv)Su^6*!b-T8_GY|?V<0JGhut}v^M;noj+yjt=8Ma
zm(JB!8u+BoWgz8{m+CW4UEyTO;A@J^fpAC8qj0e7o?CLQO-`Or^Ri3`ZJ;;o<%V*{
zfYt#6ZY$%UqXZ601WUR@A1)LP|MD%JgtSNm(0WjGW##qv`10iGlP4>2A~_K(EdxNI
z6J=NlyV9R6V1K@{q0b%p(sgahu1D*-zSRO$IRM-?jriip`DwK8^uas$`}*{5%FA7T
zu~r}3eVaHx`uzFD4B}E^8vW&!%NS=w`GV(dJF7n1VxNoQ;^N!>tO|ddZYl^XL#`$$
zu$Bq^S59=;bEd;NMG7&FBRTO=&&JIN*lONa)CNlkqQ5vCg$YNRPS~IUIeBahKQ52F
zLR!CR7go+^u?O4L(UGVP;TNYev{H(7@`keQ%Oje$YNf+U028`G8_sz~mc$J?j~Hsy
z#iU}P2bP!4%m23P5ztPyY{!iY^cH+0Tx%r9>xI<?Z73QSP&MRzeV=>KEzzy}bt(p7
zxCx7?PR%DtahlCee$|CWr#->6y^rojV#Jn?c;H0r1{82d<$^ED_b==(FZ;CN@QC#u
zL{~3yjQ9k|&K)I1U<|25Xu<BdU3*3r9}UDkxx7+cpI{ZDmNjk}yUq+Qf(N{XQ>dbc
zoO9_8)PYAqF~9#UKY}Unz6e#A3(|^-DO^&iB_>}%DZ?@A1DBU3U$uqhKSr1JtE9w+
zVeeFtx*T<!oV0=YspGl1EV!+N%R%!h(SW3Y$n_C&`*A-@Ou$0faVOr5m{Ri!U(pL#
zN6t|!3u1f#qFCD1WU0YTo07Ud?2k?_9LtNG#}?ms&uf>HI|XUbaJ{_^8#G8=cigij
z&SGL~B|3)_t*=w*T8UbY<JGJoWu%ech}vIqK7V<=qvIR0QK=q<uxK;s_*BKO>pxwd
z0E*k4dz%(rAz8C29rDAAOOHu33gF;lm@E4mECA%#z@D?iG|2;$NFu&_SC$emk)-;6
z|4!k#wCld~Gqaiv9z0kqXp$StkP-krW)P?(PVfmg;E0?(@{NZ(7h4L~DSihX=oKuy
z3Z%=@&*wd_ke@QO7=vp+z^HDVAkv!xXe~R>U|@gbaQ0D0ooWXi7NIpqi3S{p2#nCh
zurv+oJWfX#4t||Gxp_;T+t{l!UmXm2S(_+*WX8m7e^{2ju35cjtq}tX0Atq?_}Ce$
zinHCVmx<xhdpd^SCca4eGf*oxf$LPpHBvNQ9y{|>L+VQT%SVsCG)X<;w=Zs(;=ds*
zV^$mpDgU~ri{kF{=i;ScJrfebSJrj*t?OuZX1dXHO0l<e!Os|-tn1#xEcOMbrgRk|
zi*9I8-Uo#jCf@eOqbmB3##YH2oX&pVFp--;#(f}1AeqR0cXM@1y^;3Ji~&TECXgo~
zGk80V+1{5}8Iq+G{Txqkpen${cMIaF=w<ou+Z_3l$Ig<|uTyJr76M7x;OO$EMJ~}7
zXA08K)Li|82M!!!3=~$+0ANtj7}M}#Ryz{Z>wbxNfH}8Oyc~;It#_@E6JQpIFWQhm
z?zP7uCX%7gXx*T0`<6Z}r{GHcwv6)$mLv5gjP)$87t)mgo@+vLEPENtbO(7UT;2k?
zpl;*f^$JLhLIsZ8T&`NEO#_fQ!sH{X*CPk7Vtd=>HucwazlN6X_4OU6`>W)pY|nN*
z1)w$k+=6lViGG3YhaWDOcpVWASddKO6A_7zkBM`qRg{7%EbGLD4K9vs1Yi#@EGdzQ
z!d|@h?JFhICEs_>H<q4I-?U!XD9+F#?<-}%Vo2L}qJ?B@LLa+7L#j>Xp&(8)yVC0v
zk$-}7%YccC7g4CV1zkqgI}JPt&?*DNp7Y%_fZ|RxMl9<$99EnrvW>{)m9WO@cV;YJ
zotxn8brG8H9^6rP1HZbow;5?Gn5#iCC^k{t0aB2H9`wckf?oV&)QZ))&s}VcFK8_n
za$TlU(tfP|`0Or7u$*_WfJwiv*N`ceT!a1jXOftXB!MEmD+kUbkNi)W=l8=)nyo)$
zQ#^bbQrHpk>_*L>dQ#}uI{3_Wt=<dU>OZ-gkhTPj-loVq(~q*8i8ble_II#SdvIe(
z)6sD9k)bx-xSE%N2&UK+a@Hzgz{P!cdGVSa0Cy+=WrCyvKR|Ss10VM}tr?+fH0Un?
zrnYU`px||;DI^L>@DHjpIe_h+&NR(^KGc8P(tu5=spAR5M3YK9S2c^{+t|i3hDb^y
zF4{%0<)1G9?0{kJBpvPSi?+Kc%wK0^-Q)qMo*m`5-)_p$I!IW)mu9EC-ImVgm(@XD
ze&L`lD@&MULk<M9T`ZVt!E^@w8b6ri@PO*?TvSx5y%=s8jNqbrTiiZe76Ro^=3a0r
z(*(i0_x-{)Kn9EZPu#TTuP=Oem+NMX<8pLB##_$fh>*zzVz3}dK!8IkwC{FR-%7LT
z#i!U^htr?T=V;E$_g<xpM3()~Kl2+!kAhg4K?cP?Ac-tJZF*X3rb(?>v`+4dt#_bl
z<{UiVY14Y@;|sB|K#2cfZaD~`o)%-?@Oq&h_@z<tQ*6Xk3o?<K=C6`syOg#qT+4P}
zSFjW{I-<N!-rDiV{b+T>A18xfP~Bb0$QU~PX+-FvrH;whY%Je`te~(rANm~YM|WE9
zSw~_yU(O;GM>{_X>`B;HL4Ck!XLYFK=o}ULU`y!2p3=rwOLkqmT$UM6PzJZ5OF2eI
zD~K0;D2W$SKobG_gjynUC1{Ha0C)lw#wuG|Kd{v>hx+tDB4%d=<b`A9|K3We#|*XU
z-qtHp+!G<w?RHcHm~MiUQ?3gV%xK6Rg38iWdkt5m-+0H8Fs}EE)eAQwvr@oQA{^XK
z!G1_9Rt0;#U3EA2PaJVGb8_&l>W10NXV+gj5x{Ta(JRmKGa|gZhH-FX`P5gx-yNKa
z+4h($J-A;U&)eMGdP`JSf?vv13TwiZh`ZT^kqh;hX0r>Nky5A%9gM7u>hBOYkg%Xy
zrJu(zzpoxdGS&^0A#KFD$s&^=EE>$O?^?~^XL4G~q<e(UqDTXH*55yhVk;_7d}@Xl
z!$ZH+xCr0q%<qn~4UQ5d8&`yc-6DmW=sQ&1(Rl3?i6uKb|2hMBWIh*|h+HbcGlEVG
zY}n-_hJvi%--n%L-v~>*3V%1A^)Mr?)w1x`{=9QWZ=D)|hPwOE%cZ)nJ_4|E$K_CR
zRDM6Y{?5Dw4k@nEB)%SaUM(0L-l<F{;2z*UJkC9U3_^xXT<&wgMkZXKsF+HBnTxZW
z(rzA|kV4+`L*MMWb?y2Eatgtx_wtL@L^)`7UA7waiK}YMYsG%sa*({Zik=$q1`3+f
zFo1$(XqwA()i<;~*%Y^8V-mED&B~1L@5?IA1f4&M_mH`gnQ8K=xbhY2gxhtnZ<d?F
z0+AtX?c0|nzkE{e2^zMOB7Q>7`J!6nDhy#MnsFq~IP+%{UJ<qD;qL042Y;KWlD^}=
zRSd$(bV^oTUnU=Uq3WCXBZ{K`mwiUp>{Fo0@o>o7djb6t{6+Vf!H?DLROAD7vQ}xo
ztG=)~$3lU^8EbKcPAfH?`}H2&!R{*i5NdXOAhY$%v{rvO<X!B*>w=$J^7vE}$}&O1
zYMhB6_5_cOnrvu-5Giud!-~s=N<<`!a6fi&<$Jj^4{^GKZ%q5Cff97FD)T@`>m5n5
zoQ3It`pg{ghAvhj+Juo}jctq^y9}eg??|p$&CG|F76Y>LY^o+{?qg>O)lcb4Y3au%
zq3|_&-i=Vd#omKUH}tS&t4n|o4`RK?ZAZXx1eOeH+5&8b2J#gcQl6$v`y_o7A{~3<
zZE6@`qokQ_C36c-1(%MHB&fZkoJScBC~77E2?jH-fVb^oA-U$b#!W_8@qYk?)sP9o
zVqjrX#F9rRY9V^0r`pIC0d8tUEhmFzIVs;FqsWWd7#X{a|0gA8gRFeDLw=oIokPFn
za^kH-W8|QBH0@9Hd0h79RCMGk`_QM5G$fP^K>2HsbMy;lv1OncqWcHsqnZ)tpKpHt
zTmCC7_*Tpg@+Xq+$d*(<cH}@Efh6l;#`ari6U9A6MZwV}Nl^5k;%A~j31pv&uz}%y
zmw%eRobeuU#=zWlu=E^F+xbk@B{qgvdWw@=G)KzH8|ii5zI}Tga`n3<;eO6&BSc#o
zje214ONZ+iNkn{>@#t%1y-ESOgBJfS?4GA*O9;fb6!pkS^wp~kk8K?-VY4(1e=?v?
zOwi2F;xN>jPXR1Rf(X>@+HK43Kb%-<nt)S3&x!J3?A1;YgZ#e+qy!EGqS=F^Oo5A?
zp)C?DYp0t;jUi)nmz}4<Sj;o#eBTL-${noD&f{Kw@ZC1J4fo6f#2m5%b^dV5N3bb$
z5zO^t@1z0h95q9us|hX$M!P9;V>CAfz#9qSy%b39M7$3?IhwEY{lx}HgX5rVK}iQ@
zQtiOh-iP(2&z5)v)EIp^m6Qvf$)p`R=v53y8Q5s7QCk?MlhnwT+H-&pWzd-gl3P{)
zVOPB~%lc5&aURP1krIX0MgpJuVL#wFJYrUT?RbC{%eBuXsu-?<BT5UG2=x-5>cr~Z
z0}41N&3tA`nYweco@UeBOAT^UHl~eR$01fN(tKeL{S#xO{}WCs@;~Z>jppLhY6_2g
zZpZc<)y$>ka=$RsudV(RXy+*vjTxB@UQg5QCU?r2@&2$uNdF@xtgwY7J#lfRI**+a
zlt!U{`_`>)DRHV@y2zv;YRt!Gs0A1BR`NcHWez2e3=5z+1s7@wUVk_!<b&VHXc!Vf
zD`l!P<RgiJquAWJ507toQ6LQBiFpT|$7))QDYjkx>7dWBdaci=`}Jwr-C%53LCVOK
zu;cX}r95=739<4ij&{|s&{W@jV$r(2;ll!o14iczN;Qrc?r1vH-xyu(=`~%F`=joi
zc6>B}PNx$G+<wF9C?5%wdUwk{&Y+uY_Lw8dgWjGi<L$I&vWc|f97bl?nj~8Q?j$SN
zR35R?<YZT!9KFD)IqrK)cpnqF21nDWhtH1Z+A^-;gj)ZIg)bmNAwbHhmM=Mtsvl!D
z*ncuwk@>LxuMtFmiEPW0$7cC_;zKpo(-FVXi_iB_opSi0aSMP(sRP_C9T7B!468wv
zhlp~2lg{HM$S|a#|M+;PvcCQMFJ!edn7C7V`=@8H?|ajGYp`{sEI_sPgalD;wrr4T
zujH!&r*-Og;A&bfCm`77Akmo+6nmvSaBBId4dtEL>lERu_;FMaXS4|PcaNck6!uE=
z(sF=NSmHhp>+h%;h8h;w=MKQ(6Xv}FlZ~JY$;+2c7DQElgB7#G>8aj8Mu=GwjM%)`
zyo{ra`OmV_WYil4l;l>hk}DnzTxe~c%0h}_`L;YhI<Uj}E|KgC*?q8`bL{u(@YS&*
zt8gx<qIiUg;*cLlDKBW#oaGeFGB7}lJjgPT!t8A~RFa_e;m4Mp{{zV|`%lW6#i}B7
zt68g7Zd4z3KhatqfTmpacHEwV>Y{wT{p3k2o!Bj_u%L!`1y$Uy1KzPB;fBRQ#ZB{-
z@Ja?8NU{wW53rM=Z`=SRHlR8^W}I^A?r2YSBExMvZYXu-4<-7abCIkuKH7xE<jFzR
zDDyq&$qkN=uEiBOmH3g=bPx%85<O|U6;PgtJBtod{)zz49MzFe&&-ZtVC>`LTxily
ziH?n2#?xi?UV{+N?MLCpBLu5C44K|UNy+W>;-arAryd|55a^yO79<AAv>%U`htw~n
zvq^>pZ;k!fRasfPz4CKVGLi0Ob=F@OQ{FliOubT}F)Ma;FHWKWx<ktantsoNb~`&~
z!<mCIy(`k<)@%GGUJpTwMkTru<h%6}V`FYmy)ag!ysgC;BZ&6p*GR4t_#(65-=!=I
z(=rn<43kGe2>b12!`f3QfMm2EIWm6ux(AmmrzVeo*}g)&@^WS^|FjA<U6Ckg&VJY&
z2R3(>G*Et7-o@6QSxRaxn>8E5@}Nk*$!s79vQt}v?8xS>N1Tw@fjJ0Bv}h)em2zcc
zd81yL6x&D|VYq~UKwKcwILeJ-5SmwCzMQ-C)feDNv>>QSx6`ln14-cL`o)D#ed5d8
zr9TG~ZUZdMT)@-YL*W!xLfv!s1=l{~%P2Xl36u?Ae*O%ko}knimid(XVGj-yzyWz5
zz_Y=2i=Tyo0KR252Ra$zg}KuIT-qK@R?t3)RFvA|%o!+!E#CRZ_GlfqZ%s2=k5#~*
zF5x{26#sVdfZLCVheRWRzv1!QCDe2X5($jPaQW`noQe`<EhWlrp|ASCpVV<^t%MOc
zgeh*$&A(oo1i7H}!5^qzC3|ua^roPYvhHzK!M8RI`A$&G6%@2ji20E8I~p^oP$@d)
zc1Hf1h;C<N<heRHV`QADjKl%8mIx#A%uaPP9`m$TNN;Gh!$VeWMwlS~0>35CrcSbE
z8>&%pV+ht;iL~fYS_!KL&~pN`9*KCT%pWMPu~)W{$Ziy}9D-Fo_eAc|$TVLhMB?BC
zQIv2BmN0cwXj%!BZVE*p71rmUKNoXw<qc`$_*87Y0#8z52+$;x&`AbGAR6+uRc_nh
zz;l18_R${U?EU!?eX69rejkE)*b6WZ$~NTZg$fK@sb|0OD*H)_G;90K4ixb6(}&H~
z0{IKRSqjf33N<4DN0sPKKFU}{zO<^A)|{mykQog;7Q!1L56heG^whc*+*P0!^(q-{
zPLOFeiYta^a;RXULuRJ+iu96OG&v8nN_u8aSOltc3!_r%EPpUFnQiN`dhl^BD>pU$
z>Hr-w^26G?pO8pMPNc&mKrHWGYK5huGGqvVS(MT;bs1PPZ=)62vec-xWqg&0*(j}V
z0C?~U$^N*)AeU->zN+K&TXB(++-$h`K=QvpGDXV&fMh1+tgY)f`uhMxh!P|tas`*w
zah!lb*_Kji6M)WPD$j&F*o-1BZ`A-UbAU*+8t*bcERba^2+i0IDb2sRuPT1{;k}|;
z%EN()Qw@a_q)ac$_OTM4L25qAVz27=lc(xglG{$vmO7=T-~D$d*VX57cOX$dWI64o
z7XlZ6#c7^7ZhL3PIjjo_vPju+!K{ke^FntG4<R!(K;2FiHKE0pdOok1o%uLn`Gqx~
zI&h~8+d`fZu_++~Q!S<(w<V^?IBaR}S5(weIvuzD2bMG8CI=1TupISmc^0sQC^WB}
z7`NvFG9T)z9LR^fg)4`)pHNZbq3T!ZxTxhf|DtZgM(C-T*caDKXx?YeaHEm|WXceE
zAXPG_rilJ&Y+c>l{Jvhc8!^Z|b%^8rIP<}J7KZcJTr}^QkieyjBiU%nZwYRrID;l%
z#F-*JV7{fM8XJ?$TW1bNk-U>DvN0mUCcq{7+4f|!nO1xOZhemC5h<FWdX!f22B(g2
zXAEma8$}8(iuuM=<=m)Inq4nCFI@3pmy{uj9ddQvX_$_hD`?|JYz~wW{i0kmwPOyG
zqY}ZvBk@!4uBlnPF!JPI`9Iwnx#^~?vBbnlrY+jG{iC$}d|~m{=UKP@Cu9hLwAZ!A
z<VlFLk;WAahq#ODp7vHEZH0`16ADf<J^U}Crgcq&TUN#lq@L@hz_qSz9GK0b8QP)Z
z;ny{l^K!tbxpdyw8D;|BcY4%ZVNg-Xv-|<eZh^vqfR76pG+>i;6(K^+egqgiK3R*b
z<t8{nDM(}#9dOKRcBVW#+gP5a^k-DoDM8a!t8jV<BVYUZA@yP-qN2v>D?x6!=Uc^2
za_=E7CC1u_N1k8u1#cBENSpluu&fU5C*93G>k{-*tDvHQO3IU?@=UD$63W?(gCRPT
zKBSM)x~4qVY)m#{K0twl3FiS=_QuH8m%a^k=Jb6-6Hp4_6z1?j>Y^_nU1#|e9)d7I
z{wAtq<jW5UnL|%F8Y45vo|JSnktyf|;rv<+TfHn`P;#AwZCkf4QglmHJ8fZ>0=3!-
z<rnHXX&*tMD3fGt4iNr9Z|`D*DDXm8+DY1o4u^exg&Si-^<;vTsq}rc9kl_FBn^#n
z%)Q6Vgw&EH9TMd@q2Q4ee25*41DH;Rv69|NyS`AnwY!?W%GBOlzXuIg<?JQSOlI5j
z<C#To>oNU?x!+XPH<a;s)D<P8PoKkpYkd-Z6S*rJHEo`79cm03lw{k^>iI?1g!<#R
z%yGR(iEZt!(z~J~8&f^E@ChIUUIfGF2-U22X4SK(Q^-N<LWcfa1DBVp0r%ceI6o@d
z=QPSCeg4*UsYkZfy!;<j(w3UZmq#V{`5Q2FjWP-S(z{lrKcY!JmqDp-g|beGtw4jS
zaZF4CIJ5lI2ndUNVjjm`UOpFPHZz-M9t>>B<;_cJ&29x~$%2ETgH^ED66E;LXpksL
zd_Re7@qgA&iI{EmrxzjFlf++(TngC%v8f&4NpB*8Vq;kPFI+tCXw5vpVgWGFBA^S<
zK<t#>M#s0A<5Ma(WvXY%y<;YetbZC90Smxfq#UC^=Wsi{qFIwB$2)xb@cv-^<qQHt
zl=1oNS7@Euw0a`S8koXG7|7$5fOWtp4Vcdmi*?^E#5M-=RR;-+Knd~j8=P<J9~|`v
zB1ZmQw+;EEwvFS}Qb29;MxXe3KJfd|`)8WotmvPTxnpXxDg~O4UN(zn=mAXxShJ+`
z%)YR46Q#Nax_96Q(JqN4mj_Q)`5|cbWVSR)4vCgi053a+*aoI+n~30{*zJA<oZ*6R
zgUpQnYchvl1^_(Aie&u=d&_hb5Q(bMdxAZ~VJTSj{|@_MfCLOP-B|ie5eoCe@3=Xa
z^-DT3A`xl8pJWlBs(8Z!gb3>SAoEY^cWy5b7YVQt5i|~biDDMLH)9_07zMwr_U*V;
zKU;0>jov?olb?kI@j73%+7O%U`jqt&Y!6jRgzgmzf0o!I?^{MjZGk}~KnNv-$ed(6
zyXY*%Y3O`}_!$a6F1(?j-tDPVr9~wd++%v(ayo8tNh2HJ?hyK;8-og3_aA>*{bYWG
zmxlgqX)07Y=jw<zSRzxnZv*Id7^o=xrh=?ckeGeIn=qL&D_ukx^e6fdDB#{|`X_3#
zHK%us5_dX39O&fBqX`{_GVj0eR{en+l!u|B$M`1Xj3oF_#3mwQKNlW;f*&KwYSCi^
z&*<L6@JwAl|CSp*U#%m>6G~wDnxa>x(_>12^6=rM?j0^uur#J+_Cus73y@nGck(?B
z)xt<gLYi-3F_DTGa-INJZ>mfg3<H#psp&cz3b3o$1@YZl+tUw=uK<(PA21X=oPbc7
zR)qR82u+cYCae%SrxnQIZU?C<icp{znYhlz&f#XUysZ&9h%RM3Ye4LcRGNV}Z6zK8
z%)of*$Z!Mn+(^=<a!|{dSB$*x0Ol648fJx_o){O(Z=%m6U-cl?hoIcli&{Rdn^kUz
zeg|^r_Lp3x|CD&Q=+@$YCGkdKfW$i^pjF_5)(^W(GCFOjXKHw2Y`yQB`>J0|J~#Kr
zHN^LMmVvdVeQiY{5#ek9-R!B(+}Lb=AKtS?)Iyx$G#34%!txJ|PP+SWXjhZP!+*+s
zT&ZZnk?qqiQ;4(wL!8QUa_&19kF#?iS~&Mo7cIS?^QTRnG3kq^SFA=={8+C<K_=tx
z;I1jgQ9u(8?{DvV2+iSYglk()o;>N@p&dX8I%rB~!ftvcD!u*iLN)OJsq9?9a=!aN
z9^0JucxIMiPK!m!99A)*#zcj5AgiXFYLY}rPL*K{BXl>yy$(tzb(8K|NiidekPcH;
zHXT%YjLK;pp4TV-+x~mD>$#p?*RHEscl!N)-{0r(e!oBOPmiR=M)T|<?f6$~2?TB}
ziD~Z^rq1#!y>xJ_vX`lK(!^=E2H5%qg?k@fo?!n?W+DTVm<{$dSZc+<<jk2mpbK^>
z+p9hi3W;)qh$x&6O{unyj!vnYM<ABwymFlCD1zXJ6DE*CMX*-rv)XU0_Bbh-WyW%9
zC#akXiW660huRC_RgSA(s?sZJ{-8?tIT`R@ROv@tcCK=|<YAOz+_eB%X{De*qcV}(
zz4j5^cT<__c1n2PseWkGsT`t52JYTnm>v{n%~p<y=G*dCIJ3_uTs;DS85f?4;kTaC
zK|1)(rzVzeMZzUP#lC7G;pGh`m6^A+Kr`fZ|2jj1{R#Wb#uT_5(%sR^^hVt&T`5Vz
zcddT!gP1w7J&D)ijUyNyV^Ko;zgvH@C-zIm&nn)c7LiTv9F5PoeNZ?Z8K650T62#6
zD;9)BejR2jKuCJR+|VsDQ_zPSey!NZ%OX3ILSF*QsC!N3VWbNYQY=JjDW#FjXAu4t
zySg5G;$NA<Te<8yHr_x}qEQ{R@s|#awhpEMm^XQ4+N^DP79d;H;-7JDAZHse4w8if
zwM7Xt7>H_Ib{-WjkO(qzVZ0C+14V>_PyU8%UGquuK^;uVF7kRxTCQzV^0kx3p;sGs
z{G8VPO-&y9_ortY_3VqLMi@cYYu{W2Xaq?VB`}D(H-4x-&+}n5k?h4-g?D6ZU+gtB
zDCbVl`C`;AieFiMBrCaKVx^x)vfAUFcj64ov`ivrXD9M8Nn3Q(%ciVB0E&jPk{Stm
z@(@`W$Z8HnSS;T~OIyhea`3=Fi+-#2di3l;GJqnC9GV^H*_M`e(fz+jwmc7-BTg1&
z9!ms{mR*bFQ-thO5**abq>G8$`ayviU20FIq_~1QQxo=}KV>#RV0J*2D~*@z)=(jx
zrNyB`4kM7!J6;FjB9zLO1gQD%3B0_f2+m{5OfR{$36l)aR`AadM4_lhU0;x|pA47@
zySJ3&IzuMnUw?fuDUHeGeRxaOoT{m+x=0x%MW@Ip5(h4nxj*ju{siYOOg-i$9Pha!
zdw0KRpM@pJuy~U}AEK!P?2RphoS@98!(3>vZzTqu%)|4K16SbD=yum-Ip7X^dr?rO
zPV{)<Loxn`iPH}#4iXxIgW$0~K$z1sCWB@NCGJDJNac)@d#8_v6?C<!I~^BR;9ynz
zYOJA&SyGc@mB;;f9Kr{&=K}zH|Ked&ocq>Y*_93)m*A?i#L#600wZ`$&!(f}o<}Z=
zj*MKeVudBw%qZcfiRD8~_MDMsZtKYWeb;XuwmfZ2X#nViIOz8YQ#<F`_$l#1$S!ag
z`(H>bD@kf2N|Pw{UJQg)9_*qlBj4`gxzn%-xd=ce#S6zJ#xXU~P6=i!vjf!c@Nm?6
zLokd26%g}D-i;GHbOaPo!!EymL%VwcB{OwTK2kCQcN(wg-m!OWdApwSR;J-oDoayX
z6+{(C#5P~K@`RluuQ}s<>_6$pA6<qHqc_`EwCeJour_flE4Vdz(-B+sq=^&JxZk0w
zqGra&F(`I7QV5Qd3;_`!qNxRC2*+&3<D#zuZY)>zJp~;bb}Xn`5tA@`cxwB-+qU|>
z#$S%zObj&%NL;f>NHykD(m>}CI%woy91KjSaRLGy4o}qGpi=fuk%OQBUqVa0B9G1B
zcCI7xhzjV1UB@F_8D;r7p(7V^jQXWJCAf>Q*wmXqK{oU-QoCZ*F6;ad^XmR-B(1-J
z$KUFUu#hM19WNTql%25kl<D~Qi~^JDZ{pwItl#pM|A5x$;-=KKtX4lHSC08BOACkU
zlexNcC+O&y)#>javv{zsZdV9qxHxHL@rr`69fRILeDE0_IPU+pL8-f|JL6|>@rD*n
zuy&mH;)YIL&tW{zVU#UNI0DRxvFbp&pnK1TiRcTkry)UCTl)*Zei0~A?p*+Lg1TM;
zSQApBkC^ZUuoUyFB8bjH+zSDbwt+q&gbYK1K!0kRv33=AcNhIG+yN)viXVlrXev2`
z_-p;~J&I1jBt;EM)5sva{Vczt3v7?$Xv^pU%p|37IAIs1SzMj8%QQD}b_uf1NoRg~
za>*LVcPQOE45XjM?5%U>&d7tOtX^#ZoK_US8^JnZRMc_Qo~*m<DZznxDvHY}?>3*P
zWe1Qgax+(@90#GeTV0(E)FTt9PwyQKl&MH)gGy2{MeG!%-;7gdTn{;e1R^*H_l-zN
zoU@`GXlh(iG;~r%cei3rmxzVP42S|PfbR?Ls3|bTB!_7yby+po29}={m&dRrSQ|nE
zvNP8FvM8QX8iJJVlBbml<0gRjKS-X=d5|T<0tRUqAeAPfIQ7N1Dijv=6%~<9>*+}f
ziVZ?E$4A+Oj`!Y1MvhmxXI`CcX10L-NTrBV$`2M6o{_X2fq})(o83CLc<r~1NKq>1
z?`dj>T_cAL=-Pe><dp9iHT_Zc(2tm(u0RORki+N9i!tJNxzP#VAeGg#Hp~b9TKAM>
z;aBv#@X51~PVFxYF1r4ZHY=)V_2&H0tRptD|KV{lr~W>0qL>qLCPiWU3{@-efnD^i
z!s(VfO5RDY6@BVfGt%_>wKv_0iM0z+C5ssfUGq&a6)L6A5x>!EiP<p)9+NVWPMXvP
z3ZmZ6_wF4Wrh5Sn0`<yU910)%)vJ@&|AYQeq5Hm3YRwH)in#`htpSf1ITK%P{42oX
zpW6KD$vg#Q_HRxZAz5EsvwVq?*$t=c{0BK@rqZaFt?kW?=7mlOH~C?UDS&D}xT=|c
zXjk)*J$_uo^EJzyrq$$YHzd@j&YB#n{!{iD)obMOHlLj@L*MV}CYx6-!jV{j>pZ1i
z!|fGoF@?xiNw=hOdvp`R$&&1^1}(N?21AU1Kul#4m6S=)o;Ily*x8@w_@3w6cjEWF
zOZBT5<=h(lxcu*oG;W?Aaw97s0Hk6Xs%^j}`ls!b8c3RYDHqRjGMsywFXa#UC8U8|
zB~{dwgB`;1`b4EQG~$gXe;S*`wy1^6mpA9{C|NhTJT0dDwg2O(es_HsS6P26DD@yT
z9ZEV8-Tp4&p8a<NgrU0i;$QW5gM&)9Vw9%nNA@u^2c-?|QBCQD&blMDD<SEVQ?A|l
z4jEHKXh{JDHjq}<`|@}Zh@dKoCigei7VZMY9_{<DPc@oW%zSQy_V=kAQX(TnDr|0R
zR9Wf^D~(ObWAumu1jR{o82Z>mqO)C{*C%-2U;Aq;d-n*<J1J)opoY+*^qQlQs6e3>
zEG}oqCA1hJ?Jl}7IoqOWC0npIAZ+L|XW$iBss<UwTd_j&q>u56p;GDZ8(^N&ZjpiU
z%Awo)+7qjM`PDw1J6t0s$^~hApjJ4%Dz`xSgx2=~pHD2Aa~7&=V)ke?;5sAPQN_vA
z<<*0|{K%+h`&U!G{4{9H?_cg||13yEapVvQk9_kb!y1;Zw}0)0@Zz^m{q46liWi!w
zM+@U*_&qG3t(7qV{n92zBe01#Jr>&7;Y+xWa7Z_@-cQWfvC`_1k;M&NliFsUgZ>#~
zrl^ap_gJPSG*J~xBVYR*(y)>Y=TO&-z8b~CD^zvNrlK31=YJslKy!>5x8;z$`0d-L
z`ybeU^mf5JFv6A9jOJ`6a>v)5*<EdDQoFHtp6*#r4XZ`o1D6uQ6v{pb`aqpm`t(Wf
zN6|&Tm7c#)-b)4n0Fqs%;sC*HUIKEk)(s-tN=hQmDg}P<d~+w357^3?vHimqTf8tp
zvdIr0Kem(6RI$XdPc-46MRD$OXu86i#Dx!#8}*C7H4!pe48+nlK1&iUOcdIq98Rh8
zXZ9f#K1$puRI=ovlGEa#qCCyWOG;9dI><yEfX$~e^ebDh^bqh^0DcrW&?_DXMjXzs
zHc!4L3(Se7!1UsV72Df={V3he)LH?+uFF9$G*VGOsA41TR~{>(JY4epeqM<FbSU!A
zd-m=ft&>x_!KoqL(sbRpyx0gG3wp9%P#u*(5jn&pO_1nHq)pb&0gi30!!62+pC>kV
zZ)H9(n37D7$2C`mAu1^!cLEZ807B`bM2vC)`6x?k4|@?lMR{UD4wQ{pRgT^BIoTEW
zxMw>FnU9!#iO+?%Q*lUiv5dOp)sL3eh1_;4r3S(Y9$}9AEi`{|IM?XTe*Da(V!Dzp
z#*T~`)y${YWoD@cr>e`oUG*{k>Q?e_)czDl1+V8&vFNfOv!G-J0+F4mslKh6;nB@8
zO~@i`<l~S6Bg>zdjB~2eKZ417wE}=f7p-b-QtHEus_DuHIpfa+v}M{LR?%j_eE!?L
zdPVU*&#2ctvpXQ5mv#VCzpb5ApPZZ`chfHVUGiV--1x6$vxz)>xJx^xkK;328*6N%
zIEWSiWtoLqfn&RBd1<1Kp<9rqxWENqU;I2MJSXOQjC9H{qdiI5SWgl-f)!@`B#j9Z
zPA@OrFyK+T<<&X~a41?{UO2OH*N{yK_M6azuYfA$P26Q_ju3Rj`6o=r!g%ifQ(QIC
z0ZCaGZ|{cYQSbI{zh>Z90j_yd<{fzX=FH1;+tE{7XKtJ(<*Klj9GMe%(g5n|&QEW2
z{FS#S({8PAYbRbrB`(mk3~%|^gN=Ni9B`CQT8c4;`d;rlD1aNP>(&JmLIzKV-{}wr
zgX56P$XZzD*JbG0aGk^t_-!Cm=~bXw&w=T6U|q^jysY&8=Bmd|2Qm`h%5NRwN)?ZN
zgsc~YjzclBUtA<S$Be(^kwERq&dxZADIByd=+v*1`#@ZhORm%&fzM+L+mScs-Wz7J
zY<FN_HfS21gxoIT3WjYW;JaMD$ZKz@!_5hd>Ht13Ld+ggvavMJ-M`>j;*pzA$~FYj
z`HOD>ny;^zlHdRe5ksWPQU?TRJ#hcRx7u?h+B|*<leMkQY3U=70h{$3_Goz9P^T|e
zzXwQVF>BUq`K?Q%=TUTva@MT{D7HhGPB%_~Ncynb=tDgvy#Xo=MST0k+n%z-!WeF3
z2?9}3B_MSKBYKqf&W~P>b$}kC$Cr6WPPo`?L$!)6I8U?#ouBow#|Bwhmv^0Pjxl65
zkOCT87ukULj6)+EO;}brx3zcV$1B`tc~bs}y$Art()R=UU3+ouwx)pkKXpXFun`YF
zqS#I`5*o$c3C=~vAFiF-_Ea2B>E{vYR*3Q#C8{RJfP0mhpS5G2wL!VV+fy?1Da|`X
z&No=vYH}9F1Qo=RV@-%OuaF)#;|{=0>?nqXbQi2J7JKZ1$N9O5XNt8|b^VFf49m)$
zg3QyPiC#;8MA>@|<Byi2`#!lI2^8#=$XaBdkDtOFg|Ki8016DH%%H8&SK3~E&=%DY
zH#-4$*Tp>P+Pghb-bbJ!kWC`USgml;DYmkAO-q=27b_<QdVqxv)u?|93O_P=B77$S
zn?>XuWx*x^=LgasuYqmpj0dyYTE56o73SvFDWCPjTF(av>mVavqA#O77h7x;aTGGi
zB{N24U5l4wUt#7Q-v}sm-JunYiWTlZBT_*vtVbnk)o(sZpA0Sl%xI6}npa_2-QHrK
zDJ7{NA8OmwzAFSSjExyB8Mj+Lz3h<yX&8Yd$Kmc|ZuVr#?!wp=V1`FrHt@HH>^WDb
z7^LPsF}SH;%xu7`YmWwQ&$#kgAF&bRZAQPi&*iXZ>AI_dM&-fY@AT`pD=jT;{le}H
zcJ?I>q>;b=5C>jCTkMTKlqvr2<rz}21++Bv26gqT33y9oK{fGZ|H8!i{ixkw3kzJ(
z*HC>8WL4nII?o?YbO81o$Wrf-8+evtM|d>QI0A(ur2AgrA2$zCKGD=RsP^_JUG9vK
zQFUg+)F~4%r{Mj@B(B=IJrrOuASUV%t8ux!L*LVBJ)>3Jlsv(p@3k7vqy;`8<v*nQ
z?=?}cU%Pf`<r{b|z7G&e;JFq$rI8q5h~FP8O}d)ya`m_R$z!7GnRWGPFH60-ao+=m
zs0V%~7zO@`5#$Qb`f}$>zdDphWu2p22IKgJtPf*ymZ`&R!55LO3W`F}e*X6DPvg%}
zU=p0;8_K`e%T0Y2wzbCt1w62x7)+o_Pp&%c|EOYz6d{#-+6wa=5Of8CXFW<3I|eh4
z)3fW*Z(GATDL9&X(5*I_rq*yW$3=)I%SXI8SuQ|%JA;D@`-NstRMjEpOUcIw!-boh
z!$k!1uO0|h4*fydl8~Jd6^Yafnh-NlU_Cix=3pX|u9O>+oNBrt^9YvINSkNdUT-+2
z+)udF&q|S@@&VGapb%D2OATjtjTM|{6ikt@HUYNUabAw`5js1!Y}ta_-_IjTH#lB%
zcPf^cimgW!`B`8B1z?m8`zx&&L5oRVR%mh6a_t|Ajm!;C5*N9<$5U#54DGc|jEaN{
z$N}Umcq~P=ln$irWqYukP*zaKmSu3Kb*Vh((&fj2#C?RbZI+R569*y~oB^Aq<<`Y*
ztYlDdmUT(CHlpI<z0{?AEn0?QZ-U_RnrPpmz*s$-zng0PC^L^xHXPBJT#t>)X;Ku&
z)AK^WSxxOHYO%A!;Llc*(|n<%#G$5G6)MF~!dM)_BIyxK*|nBQR~y5OTb;T{p=^%v
zp(nK<a4OL5=>dP)ia9L<4bAGJ;NaUuaXLGhjEF+gIkt3c`Nf7qOe*MAH^M075P5>3
z$aJVF=4OJ=`uOcmefU5XQQ?>HAiw+$d0z)zh7A%rO#l}cLVHLFN~_p>(w>xNSd-3U
z+ACCLsA;1Z_hH%#6tBn6CgvCaw>IE^=oq%@Tt|}6W{K-*d01kdNKFlxwW0BGe)T73
z;$T_&!ulasIJI%o(4n39noyCnanj(y9r;?oAhrL+P|-MY1tga9d?F-P$+H<l-AyJJ
zhLf>$nU2Grazd#efUQj`mMJn3BXjwnTL(VuIVGcIXJ*X+>3Pc5IB$IT8q9#_`f=U1
zB1{xfGR)j~RLz`-oS-$RD`s*V3(84-LhMWi%A(p3^ZHtMa0|x4Y#1*U787|uTXVx3
zsBA>2i_Yi~J{V#Z>mvhRqjABI*&kd~Fq)w1JB<GA4ttF0^;fQ1bvejk>sm*%_O9)c
z*tL~4j@0Zzn4D^A`V+RVzU6+|TzbRtA<~uK;8jj=dEX&f+}gw>k{90i`Mn{8i)W06
zjy5!u@o&Y*`4025sL#pi|75=oal0Kh6o8Z<c$D{<etI+SP+X~iCmmktG#YkSfMmoK
z4Uq%2$~rw-8pMs-x8<wAvA6J<f&M!(-g_zdEy07{8vxuep`LhI18mAboPk^ZR)nrz
z=%^BWWDXPFj)=@Qk3o=%R4s&n*EEQokTRRm=*0wH0m#+PZAr!tfJ7}$fGEZmG3mm#
z2&pF2%bu}q<sbqX?w8EL$<`OD7!h5_GiQYs_0~}4b$$$NB%w_uLJ^670&BcOd*YzV
z&d%0ns}L`@85fNje&sQrq$D;ZfF4gnh<y)!gELfE@}xPeMn}qHvkeBr!SkWAm--Ag
zkoHboUg*-FQTTL#`;={^3z*h)P<Giw{il!RJk5%1-FT#aTgwT@ROzEfX(3pCNz(zW
zoWoc__>{t824eT1t<|<rETHBSI7}!G7Hpsp*_1qeDUlr+{Rm7w7mz)KZh$>OuzIw~
zA7mO!l295IR{ZQ*{=}V-L3^;DV=qI-l7EQ{)|#gChcUTMt)ZkAlK<1K_sA<EZ$wkU
zaURT)Mt0oE>OJCBa)~VRrhHi>di8^2wy>m`16{bQ0@XFsk{2l@(Vza4;noUnsg$6!
zakUeV5kkYs@gPwciuA_oDF=wAX@b^xdCCAOwgF;S@8A4zI;8zJq`z1nY4kVV*awPX
zrtheHZ!fRGU_e}UT&esJJ-zr5#VWDV$=(yi>0D>CtB2?7>ypj6ool;_?FiMI2*fv0
zETY4niqI1bNMHkYiirV0Y#r(|@oeBP6hA@UP!T)`LjLW_65kEHG7G4YsONC>h|F}B
zl9jO?uiGk~<Ecd#x>1m6AOcv3V>rL)L9XW&$><R8(~yd3$Vyikq=34s-H?K{a!+lG
z9xTiT3X&=+47^>oi2wK)y&97?UjWRC!U_ZqcxVYlfE0_u)roHoMY!6?v1UH@G@R=<
z`}FB@mIFVV&~od<!dKupZazs~!WMbGn@Qra%m5sU*2231%y5A+txkzrSMWY9#wMY?
zzun#A!QixZC@14pQkHs)MojM__+kucy`DER;On*}LZ>$M4$mtJu|YG{zfhsL++Jk<
zfFb+Eu;zk)piUOot|otk5;xql?$_5BT5hd+!g2GGp(cBpkiwSNKEyhaqjdql?f3*}
zlQ@+-#hR6SDZPUg!$j&9=YST;Pgdw3)GMg_#M;V#ODJA^DOL=;^Pe+mYlv_XdSt)^
z9d=xu+rY^=<`<h_mTyr@^O%=Fhw;d#4tUjL(V~dNXq|4RyJ}m%nd@C<=(`Sz^*gGJ
zrjk)wW!hft!E<d_`$@0A;TCuuwdyb6Qv@1_&D>-Uj*j$0Z*sMtF`6SqA~eSWv|Wt#
zsRx>N#A5lndlsUYgKk+w>NMK^^y714Z5--uLoEW4C+vB16LY^BMESt<5%K4~<9QCj
z%i65p+6*Gdh-mX!0q4Fc<1e^{5S}aJ=uNy?#|&9C?dI9GK~KmgOKyGby6$2FxS!y7
zd)IsxL)RhtC0ar>k70@I1G&gZLeg@_kM-5}IS{JW2fTf&SIGV@vFlORb$RGKWI($w
zVIXDxP6pPQ_>O8?yMJ5NU|;bSK-tcZ$j?~ktv<zRJ9WVS0UTpOIozBjo0n30KivEH
zOOZ*7|5oixF+bIygpSY6_cb#Rryayy8eq|~a>d?wkK)I1EzG38i_tkKUBkJ~gO;8F
z-Zr9O{gx$a+y>hT;|}@d-h%?qpi?HM3@u&X!MLs2n{VlYD>%?TsLAV0pvYotz;1J5
z@u}O7#m*l5wf2)>G!ZhK0#_Qp#xDOf4JUI8Ukx%b&YgaI>r>VK>4&K^zMSZac`Y4Q
z8d_quBh}8PeCpb*o6Y$Gp%RqJ0Z2aQO=#cp03DO-mGYjSxCS_s7ZL6RkW(r_p$^F_
zEeumaC6#sO>xVWsVSeM_tHYL}S)8)<*}`-|ZiH}}V|-9lgd%sM=*%2Z9stE7q6E}X
z%wtA3-6e(d#0x{>gft^@f6#r}_GC+2<O?LekbfmEnL~Ym$RmfAgq*f5Jp)8;BbqA=
zh{xMT|0CaM5-<y$L(JljSdN4Dwk{>NP3QdR@?o>8L<qO~UqL<E4BL<Q)X#m{6(b@8
zw{-{xk~S7h8-$`{0erp`9lVJ0{^F^Z$AgkmKm!PKk<6?ieTKqAN{~&yM{?7H*f6Ro
zlR{(yb<}ujpk^RF(IfCAxUvKFW9gVL0-MUn6s7vI;>4?@c3!5V9QKWkH>TI7W27Q~
zwbWLeugsRmj)JM}i57nfar)rhm23g*BueO}(zdT;Kb*+N#EYi#>2@L!wz-B>@E;MD
zMN9&<wFoP5`H^_@yvl1QAA#bPX%B8;QQarEe)!=!U@+*wMRK@UD$~+3{xpU(&mfRk
zVu9sqlUYERPOWQj1<8f&iYeKHO(H*{3g$kNB2H!~0A`830|f7-VLG2$?ti%Eq`p>b
zT{|ouarQJKJ03?)va}PUe%vSU6DL3@eCQmh?u3vPscft%T8M0p!b?CYoPJ#dCvuGV
zJ+cZkoKWOj92j{O**398gd3m@pH`0r?)drigUlhwMLA|tJ0W8Dj@23;Oo}L=(Jey;
zD@O7B>i8QCpqQMK?I-iLBE)9&do-d(P1A6m8}=n#I(Oba^T7ZN><NsxWO}FkS_~a4
zqN0#!d;u=eJBTwizCBvRE_!_!8dk9!H9D^_=5dIRAa^8+H&!viz9*G8x(y*)P#RQ`
z4k1}L1MlgB=8YIM&z;)=gSv=%QMR^;R!D)_DwV1{a43+bvSC`SdfjyUPWP68^|Q%k
z=9G8?@3rjCz=)(<-@jxZ270`tAO0T+A`n_TE0H#|J^JzW)I{?aL<cphyP(SL1V+W7
e|MsnIowcS-(>r<jYM}=In44NoO`Nh|^S=T3rPQea

literal 33182
zcmb@v2RzsP`ak|@4;m^_i89+pRuK(Z85tESgp81xk=amYqC|*7MkyhqGP9BuA|oSY
zgzUY3&zCyqzRx-L{r!Kx=kdQEk8`>!KHl%wxUT2*d_J%1b~`C2v1;Y!l@tnPm6W8I
zB89T>8HKW-aQRaFiR`K^i}1@q%i}7RN+!CN))&k#Qe-b!ni`o{8X0J9v$|+*VPJB3
z|2}T6ecXGt>04TwS{&r$H2&vT>@zXf<FqiD{f<vrVJfL=L7}X<K>oKNS~SXlLb<k5
zO6-WTO>l36^|{j{b8`dBPMB>wdRbB71n-hu7dy?TzGwI64Y#Vl*?(;B7{5jH;xT?I
zi937to_Uz~`CQxK<0aQz0|ir49i7HoC$Fy9LH}Wia9_$6fj6bLp<}k`FBkc9Hg-6a
z#`A3U5*H)??D4#EY1uYr{IiaU_8IwA%SSod-4*{FSA4RI{J};kmuKYnDy;w07pUwx
z<jvYz5l=^R65l4(*4O796jV=@S(j`)6*@XlCOY>i$?(j}b8ocN+FM(1WM<A$rFh)A
zli$?D#L3C|@xk7rzRbCh=$X7PDdqY)t@&QB4Zqxx_S^OC`}gBFmaba9d^vf_><ld}
zt>{zFH(tJcd3xlF24{n{ii%3`Se$Z<;^%0E8y9kJnN5xM3L4+IabvyT8MRkVbB<rX
zeyz!L67By{FniqU=U1te%MH<|Uu+Hu3HkiutpAGj?54eSNplQN=2Kl!p*C|fV<iu^
zir5D@&P*yK>dFcW3r8zOt=4dyVCyJ-bmHlbR_oCo)wfr=#a&j?_K%LX50!~_w3h@)
z{b-$?nHnD-PaD<~9_?U%68CVw-omx`NALVYo{RclQ@Nj?iF5pZ?)yl*Y%fKO)wruR
zk>iD05>I-_Av=B!`4HZj0?OS(cB6Bzy_+1Tyw1O~VzYgR-@m%taPaDAkCfl8Q#Kus
ztkn(XyqQEJH8LH0>XJP0lPjMbTh`Otd%$s8@Pz+9HbKFFHx?Z&?d==&>NT8Z{LZFa
zR(P$ia5_%CB!F9cT~Zn2p{pmKpWaKsuemN%bXeKup4!CNb8pr;3)>F9(k<D%l6Kdy
zw5@8G;#28({I>CG_ul3zZ-=Aep7hzzPCeKE^mswe?KK72+1C>F$`Xufd9L5M@sL}4
zDV|U|d1mI!JFDI>aj(shUxwOCw10e#QGR~f>&T6zK0?-)_o=6SARkfpdS`2acgKx2
zB9eKop>G{$4q_9+Pd+&+6C(UDI(kQ>+#~7RtGBA8T;6JBWyRUc!o%Z>bqbvE@x5CU
z8q^^h#P5X<D6o~+s?X2OHJzJvu<C0p>Hn4!A0PiMXN{<g&I8}gILVT}8+Ivwh&^d;
zWyP)(DRY0P68p&Y$+@3j-z++us9Ul_<yG_UvHjZl)K<N9d1<yoI2wTlw%<Sc8Q>9_
zoTj-QCWmpVR@Kzk2N`c+VDR+!r>lB?Mz1vZ!1&Y@$1_t-<><S$cAdSwUXLDaJ$8%w
z8_sciZ%R{gz}SHU7t2Bp<(aD`U7~${`h`|cP5f*9^7pUPu&}%a6*u>tfBPv;LzLgR
zP7D`Ak@Z$YU80_Mmv<2MegLPtGEq-{a<td*l2W|Z@jzaK_fesa?wOgQc^-5f_z7|^
z?k-SyXSH|iXM;8#NASRb1@fX>>XHl#@Cb4vKdLlRXYOnjq8GB-GdDYB5;jWLR91pN
zs7Wzls*IA4lJsHL?G7<H8!o;|E>xuCN7eIF(Q1N^Ch2@O&@eC*3-zVt;KO3nl6KMV
zKHY{hG7yr#YW3>;k`k|1ueh-1n}lt+C|7=b<~E#aD_qYm8z@%w?9@)BNb0RZR&6bL
z9$A$;SHv4PIgFi06bNdLF?VuuvbVQy@tVR_*>nEweVpDP+L(Crj?$7(PmZlvwd!JJ
zq^xc?GYd;?hJ#R&;g?7p8?ocZ<FNy*85VN|<>fS#-Me>h`x!G=GdA8?9&SHeE|L1~
zozgoi<BfY%G^^!RROk^d!m#A`cb#(o=(l^n{-<q;JE=uPL_D_$+?ku{bF#6q;j-*J
ziDQ_L1>MZ?a;(WIlrv+TxpWZA(%RmhFE2Wyqh{6lX**&^0KajdfvT9;Vzv_xbjagH
z&1#I)6cp(5@>u^ohY!&`9g+Vr<dBedzUOvk=IdCiwd>a(dn)Z$ES|+A>gX92#o_4a
zs9Vo}`D*~)V}ZOx=fXvcZ2Qv3cAS69d!@VjVr{}j-QN0S<07&M)YK8DU#Q`oDxaO&
zjosSVG2`Ls8KITuPAPu4|904MkBTVyP{D!v+FI^QpLZA;87*JAa^Yix%E;l)@|@U)
zcYPU#n`6AIaCQz}`Jr<)-KtkjWW0HiwEsR?gd1G<EKRO}>Zz%z$_xj)jH#bOKdN7x
z=&E>XfDrZ0x{p6;U}#7i7a)?Ek6+y8>aFJEKO56e#Hpu8pM0`#sH4p3Lj6r)`|-Qn
z+W91o;Mn*_8=JR%xG>qUuITB}Q(}sq*_xW)-n)2i6?%|;W0_K{O1%GNC46b6Q}TYj
z(g?k>kjN`%la0tt(S3h&1vQgMaOUi!2M)y|`MDtnt9RdWZf7bM<Ii?`GahPbux^rl
zC7X1q>chkR9Q7$C0%vDu#+tOb==Ez}ZC|o-!(&{hfshbSc^Mh%^73*q35lWpZ^y`y
z#+i*#j`8h!ZF97Kr2ESn4Gj$}{m!$=d+xEzYT<5DaJb4}o);>8BvgRdq54X50pgH0
z;+D*#gH^F{*v#giKTGjB2IXN(WCM9GAiI3cbZYwCjxRr#X5*t<5}4=qRLpH%TUlr*
z;&#bvqoxdptjg<r)p41#?ny~kf)$d_92y-sVAisDZhEMU%3C{LD{qHF*kbZ3dF!`u
zW+BXEBcLLJr^eL0HEUgp4d$nHViEV$%=g^Hd+D<)BD!Ln`k{QUEd{ZviN&Ky#`XMG
zJvG^M8ur;=G@MFaoK5L$c$cDjB-L*0a$0(NVeo<dG&D5R0|iW<W0W|uwRRz3AxFC4
zW>QWft*vGd)cmo3&mPYre@=_uI=+1x8Pvji$H#i>_1v8r(`@Z0zWXb`JogYkxFS+^
z%k}Hm#|MizOGXiuoZ>aJ7fud$<={zP#m7If?rRhi7hfnZA>Yu@a4pKEE7WPWFj^se
zhjR4EG^hSUMU9OiB|!rF&053~j|%L3u<!gw?8PP?9m%wAZKss5@bEWwWBY>mjkOTS
z?D5EPuSIPgEPrT-DJtVnT0J|{ToV%$4K5ui^kuUhDiM(F9&9fu!k);o@X>Lq>mc@#
zEisZl+GBO$!Ud^2V>pwP)YMegn*6%D&2)7Bf)-r}S1}6VOYuHSL*$N(_av4Hnzt>#
zSoFZ*n<Em<M_j#<2j6kSN;|&}d5W_j@$x>(*mLG3gXqlgdLiqd5m!fk+`M(mms3N8
zT`pKZaJ52=BHJCtLm#g#T2?%{>*Qm~qGhXj>zz)XT#Kt5ZadUYiPgwtJagvD;vxKG
z@!+FL*Z_t@SMN)BGx{8`&>iimJ%*bv%aR|jj({SN#LQhl^Vsy;`<{k(bT(=`OunZ2
zY!SG8mqVUWsfR-@xEUBK7g-2TrfFg#k7S!_`fXv8{m`mKOQ|0letDTyDXJA48yg^C
z!iazq`F{7ogMmw^HU?<nwm41T=pDH7W5d%E{!2qPKEn>kn@<Z_^)%z?e|~n#<A6oG
zX-^GzT3Q-O4=-Q7{QCBa$Bkuc6kll`S<NI;jDL+j|Bj#J8ay}&yOA`5HKOk`##^Wk
zT6Ss%Dw_5+9>OZi7H}9=$C7=Vo}KCg#QL%)5@3L4^Je$-^h3D+p8F5A+X51W>6eFb
z8VxZ6&FCWhj89G~;)QJL5w~}h@-Q(m**iFB*k%r1)fYodQO4%qd%?M8&6-3H9xbYe
zh*a$LBI}Ck>H-4-=qtMsxh-09S2Q}!IUrmWHN3ON&0nXAqy9Pi5`x$GXuZh<{->IL
zl}{;3?kSSr>q}Mc>pA4oOwR&=R*vD3-q+SXT(*XhBHuLUxBE;>OUqGx{T)CvTG`i^
z1dBR_6nHZQjSNl4?^29djtIG5R>Nkze>)JCmo+aRqIS~qRja-uXA0Z&J8Ku*DNnbv
zW)yWSE)SRB-t2{K6_9dDJN$909a31OSu8*(KR<uu(J5?ClzRHr)VFWV`<st68*r=Q
zXaUkqVB_$O0F?n=H523G{hj43*bAe&va=@X7f+w;C<&soIoPsFo+?{(c08x&=(F7X
zHS!YGhlGVq&CPi{n(FJf$ji$ojw3D^H`))$R=S$m59Cz(^r@81(k!@(qntP%N-Jcp
z@y7h(TkF2dn;Qh^sdcApN5?ucYm$w(2$(cRSag)GNOqfPm?VprY_tj4wFQ^O^2g^w
zBjvMuyv3D|vmU=#63CY~nUL%_nPO!=b9<S*1nsvjgUXwcyXd{d-@kt^6Ls)gm(xuO
zP7!}eqG!^T?$fuZH?7lKJfOO7-#*<LTU%QKwkw0PaY5Nrdxuy~S65f-j%`2xTAv0_
z@ExbL?W3PZ#nTh_*iLNx+3-#;`MiC>v*R8csW<W5#Njs^@4tYwpaGcVtGNfe$8OPH
zJdJ0@w^0cR2?2MQUb*r;>)Ilnq6c0C6k}f(Pr1q~de0;l3>-%QG`iH?*{Q$T&3>%G
znxN^~+1Ya$_O+JM4v6T~^jwtjOpmd3Z-2~Aj&w)%CF&Foz8}YZIPv7Di%fXq#88L4
z@-*U)PD!9&@Bs@gV`Evb&3xoGh1w6U$ef!M0y=zh_}aqQ^Y1p=T#Y~7W5=|`sYkzm
z=rV4)=5*P{4`t64pRVk;Y?}ox-nL_hE8^Htqg~&_M=k^~uV<IBx!~v)kJ#Uc4VAvX
z!$&hn&ncz3Yl#7ttv#_!1cz>`+2s}N500T`OS3BT*37*#%a&3zCvz_$6Ieyd#H7qy
zbXF4EC0oRK{;e2dXQ2<vG8}qVX6E<2lOy8;+8J}RcDP3~f)<U~I(i<R<=xdU!X2hY
zrQAi4wm0lm8+M^vm0pZvTXu8BdJ;?Zt7A8nmX=b6d+YrH%QG#f5G}cNi|HN5zb#w6
z^&kO;vf<YTaEYmqQ+2SQZKaQb5-t{L85(+|qzEiq&5)I!f9t&q)m)TPx|_l?<(-4y
ziwf|p`c~YZ5v}5rli96*e#M47#8t0E&aRvc<TFgLpD-t%A1U*YpeZcB5f&4Xc<rW5
z2D^p<OBQ7LvYq(wVDH&rdM&Ev+?sT|l-jbO#KisT>gq_<kAU?)E7ypNi<^)AJil_|
zo)77EW8*;A^M!x|?le8G{#q<+YxRq>%CRaw3zw|qy7EJLcD!}X(W6J{xwUSpPHQ-f
z&?01-X-R*4wAOKM#u~Mi&Vw5-UhGAkdh_N@iah6PJF5+Ir#iw#x(n}dAQX(bgvYFK
zdt{EdI2qb{_kOt29P^+W>V-#6vl9hIwTV%Z-{!=Fe6=++MG{8Z3hxP?IV+ke3;3a$
za`{p1sS>J<dmdwviysO3)3At>yIfh-COS90AFK4_)brCec6LDyd?t+y$UtHm$|JFM
zV?WJ+$`*Gtu;l|_k!^n@WX(?-gW`bm_8KO+&ytqav8n?jBLsy{Pj<&~3imRhZc*!L
z$_zbrd-b>8-c`a|&rhM^m9;)DDQP|*$nXq#84gq9?Lj6oMFK`Ohp}V<f@aJ(?Agft
z*qneo)Y4a~U!FHSts@HH=<G~swC&ic^h7<w-nO~xJoVRx23d_1lO|oDib$Fwe-bQF
z9G4o*Au5^;v>cC=5526GY~80$!u#~h%qD&#dIbdq%f7~j*BOBN2r?)oBz%~Ue|RJ$
z@bl+SatE=_t!-^OfxB9|y4+BkeTmZ$@Mx;8egIr{P|6|=&zkl4$c^HCY44ooM4YAv
zZg)B6V80OmtX2;`U%6t%_FcQ&&A)$Sv#qZwyEg7_8PBj;f!62CGn9(OK?2@L@!z_-
z3Xzr>I#wvgvm7Ewf$!31$<GZ7Th`m{vPO2_u<snbgoFeEJwSLGf^1LD#Hj;DRD?^c
zQG2a_;caINVp`<x??~|a2e(cF>ki~^F=4f79Y@jx#HJqYYckpOHN?8Bf^BwsNWQWg
zv5VVj*8XQx=A3l+@pupvDyT0J93JDjzNVVpK+ZSCjir-2ZgbjW<KFSkaBovfOZ#u9
zhT|_)#}=Y$dSljlt7~DrJMHd4q?FmoZq7ui<PiUJ1&qxoomp8~Z=z6%2Y2%0OPn_f
zUfe%D939H=&xU%Vo2fPfEgN>6%;NQ3A#WmeI#z|7Bqb}3g#rQsoB1x~`fE5AA^?;7
zNVo5tCJ2DEiS{73ea><r!i9)~hP&*waX`JWaKTdd*v$spqyqVkrGYvPzP#M(LC3i?
zME%uRkIT^m=51VFxsJdZS(QE|hzE&4x0?kn8%=6w6&AW7C+v5aw8TPqBZ6Ri^>BVv
zR8`aal_!S|TK_CwBRYK;1w`lPnDqb|><FlcYW|Jsb{ua*Zwfn32i)V3CwQ)MS|y8D
zZ7L!39-=Ar(nZ({0=zeHstXqmJ^emHh_JX*;EhrprucF1nsKxUW{TG?2yB=u2PWHf
z>KWI?j~hmN>m@Wbn|Jq_psev^JQRqk@;Z)kW!P~ll%jfpiF8cJML5o-k+MPL%8=lK
zM`U)Iokm7=1FGRcX^K6U?`uq-0NOUFdPWPBFfjTh)l7Tg!i6g7SFc=m`GEuzuwQR=
zzol|HXc$7&Xl7p*Tq2{$Yg~69)j6r_PQN@Sg++}~O=Kr{u)s8<M|6Vc;>WxD_2hu9
z3h(c%JTZon=LpV0K8kIbs52JdKjr~j<YB`#0_4pZ?QE_JxF8E9YUQoGwT7t_vGGHY
z04F{Ud<Y`VIZ|cS#B0mC*de8;CSCIDa*T{OLtNQcs^338(E1Qy6uehEYJzWG0*zT;
zzW5^;u#FG(rvaiVy)pl8(^QWbaWYb7(}O*#Shn?`8n=NcBm~LzB~&~(>MzyPKawB9
za-Ywzx~)0;hOVe#V`F1aW4e%>LNyo^LLgv$ABsAO+_`gy)GZ4ZEp2XYz8gLM&EQEY
z9v=DOJubWJojZ}Jq*0lUx}=;r5et0XUoOE^{`?GQ;`=c~cnarC`0ix=+fkWKwu5ci
zcwEFb_8)p`ir#($wVTG6nSFNvzY|_(_(#?5q+?QM`0Z2F5k@FRrNWI2vTGCdR;*sF
z+njZ+kiWP2%G;|WyNVv{4adD7D7{B3)lKMC$uw+n846z2OvgjV-8Z-m<?g2Ox&L5v
z)_wzx&lfPA*8y#OcAwdoDB<Dmnzj#t2lX6{M+D6&@@u^0F6HB(Z*!SrPX7K26yAi-
z^}RgKX%JYh&&tlOeQu4uvGLP$l@C3AId*&*-WA>!s4#f*%f07GNwlX=pLV<S{OG9)
zUVzb`jShz`hl@g0Lmt%DskOG<mwgk-vWZRp<jby8;)Q(SZ7bq9&**g+)zn0v^rL>C
z&puP8=~klfCX(r&UsUBg=;>A{s7IsSB{I(=8#rgL&3PoWMln{!Ypa5n>-ZR-XEgiE
z{x7c2A`DVknEI<)9>r|E<?1TwZeG~>f#bz<-ROyg$9SUDPW?qs&M+$qQR7Xe7Q~2t
zJ4#-SmGN)idF9_P%DN5U?1F;My8p~6D7fwH?7X4jHcnWC>@H=tBN-VP1eGV{tfisx
zp_Z19^j%zAU$1Rq5?XfwUnIHoDNPl1F8D5-yXKCL+wa~9;bwGv@L@sidkcw2A=yY3
zXs`gWeZi2@916c2e6?|X^25og;Y#@!R7^fTJ`{!n<~PCeHGlhdgaC>I=B#6VO#(@o
z)_sh)7ze%=`A6Xj?@@c*$*0SS%{TB`Sw*djz-jsO>%&!B_;HjE18LR*l3%-a&67zq
zq_;jL5#e62z6u;RXo3A#hxG|<_S#@Q^25c!wnD*!2hAsk4N#jM1{GMFYQ{oP3PRgs
zfJ7ur3VCisumIduWC<;>+vji{uVgO41Ne$ZpDfV~6fn8t?Y#yk@u^vBK8k!EqZ%%E
zI!?KUw^w$mCa@x!TBp^o-oj6fphgNo@jDDsxEVV&GK47vpIoYXh8(^1%$YME{W;6P
zy$W6(-T|oBJUualh4)96Q2+*zey|6@Na+ItQn!o-wz^_%i9(6yO1gbUlOiV`?4b|}
z_jNJQ1PZW%cg83{H;Fn5&rLPW?Kt&p!=bCgTrY%d2U$S|<Q5g}F15nDurM<(q*z;9
zR}SK>6kcg&&po(H_WkTG<^A+$>r-!ktvfidsM~2~gf2Nb`CO{$HH4|al_e-9H}e}w
z65_$AwWp`pBy&dh(pZ8GIe~|xX4zJdh&S9-xe1#Hj!)~;<0FyphkzH`5$BQZYldmJ
zZY@FNdt=qR8I<AT5Oq`9ZWJu%-dgTFWlk<{QPj~>>%I@P7Eo{Ibw%v0Kz2a7$w5|G
zL8v_JPq479uMdla`OmKh2+$On8CE)a?3me=D^Ed@e|~<(8-&6@y-6m`x^*P1tqayA
z>PQ$q_aaWsO&1q}y(#C;pYN)STC-rmg5ZN!+!6V?5KQGB9Xt+v*Hs?A41wpuKucaE
zRU{Y<QWJDFWr`Ztz5ezhr7_I1t0Ly%11y;e*KX~e^c!LokGFgq>l854zH}Qrr*GJ~
z^TG6pkFKsxZg=k3PArYfs;=J55oNUV?HbB_tYEzytIYCWYf5X>{CP{NtCyaki~79!
z7_R^EH*IDzy=xU+5aGxXT}n^Q{q@a|b3nlToeg^iZq030@Z;_K*|3B9*8M4$gvI>)
z)omYqj{iB5%?By&NEM$;G0M@>fqGoI5uF;255(R?ivBZ@A=()jSaSQ}&HqC3s$e)J
zHMGv|yQbR4pm1|pQ6A}#$LA`ad-`@emF#Cxr}zb1+U>#~`)u&7NVzX9_x6yVB+t98
z6V7oP`(%2#aEMw=e?>dghkooUPo0QB#C!d(5wFWm%Z>c_2-W{0;_-RmJ2k;##-%wR
z9u16*$y?fiO#yaLw{^n8G0*v39uF0l3FLJHP!O5!&pA^kvTYk>%a$OWJJNVU*6-0L
zWm!D)=SDk|fHT<T=k>ujH@TTi_U+rZTXt7_K_NQ%*3tlHEe9oANgdAqZEumu<zO2w
zeU8os=g3V@4SggL+7+lqX9VE18HwY^xe4!n`h`0JDah1s1x!x7FPug{JDHktfe#Pq
zY62Lpj8)waK*?azL<$oyn~^x|U!eyy@&lb02XNm2!=m&;jSn|sU|?W77uVgF=id>K
zk5~mxRSz{1QTA}&KY{yvpOd5UeJ_%vkENW;55u*zw8v4+6@p5}h1bPRAlJ!lJ%{;^
z&pRpPvc0wHl|~?3jvS637OS2fh>X4;5B?hrqmJ^jCIU(a*uuq2m!gQ>h?hPxH#@U}
zipnEp22ctpjSt{b7lBfz(07TG)0`kn%CCy$5lXED%Pz&>M~~JQ18@0}H-c8!^5e(K
zEUY8yukTZRnNgsWNqj(I&tp5N(_Z?h2oVGE;i`)@$@CRMk0zZ~g@uLb12f~!ZbxNK
zL0q~G9s<nACK6NeWc|a#ItWpe4ZBZ!Vi{=|8SmV<v1oL3w5GNedfZQ&F*6hv_(E||
zT%;sKng8^t%SvRA{Q6l$Bu|C|z9^s<g7R4=GSRmFa$}lQh_EfiX1J3Efw#HIY3?Fo
z$cj<g=g1L|ErRwwhdztlUGNyF2$I(gz?{}^-xeGOV>ymDTR*T5`m&^W_|XwQQ!A_d
zvNCU|d87(}9+r!MwZPTQZ9$0Ks%W*OXSG%kNMwga-dc7YMNE!4_lAd&kx}`Dn%}Ke
zTUvndn)&nGY4<xY)&Io9MqWg=_=bN`ex}^@^!TpBC|Wd9_xw49s7K8LII*f99GTnv
zHO=-Os;qb@Bw&<1LPMEQHtjdmHk@jj)$Jb~)cW%BJlP!ruN`Nu0yEd9m}p$D*ZFvV
zXK8|-{0tIKFbGw`+M#kDs-OpH*Sg1plXLg(=l-K?^C5YJuLemOMfnAAAj3Vi_r@CS
zygz)9Y@S=011M@XJ#LoR3+Su$c579U`@2p1bxlEKk())x{bb{MNR-=fk?p>x8dg0!
zj<@al^kfnAixymixUY!6u9Au|CmmLyK9W#Y-XJ>NzX(|KBI*aiSvezRF8cJwLXQ-W
zC_LnTGn&YuC}F6a0c6Zu^H+iXV(1gW{})5oz*{l_fnUH+J(qr!mXk9M@;EqD>{h!6
zN}4hU5}sHetgQO-7!^7xTp**L%ye`B5|IFyfKqhbU_%m)esLh52daUJ$43?sZ~)E?
z<>xXAjt42Om#*4uIx{&UI7KgFFNl(nP*~xY8{W!<iaY|XUXg0nI>(R++BjU?OA9YF
z*VUy$BAC>Li_>w|zI0N@1>X0So3!Nr$`Gs1&~fCCjIc4cXoQ7pD+&esCnP217w$ak
zUeMhWylP8Ou9x2>kjeOGkMIA08UOkVW>S_FdqnV@J-Y>&Zyucb2%Z}hjI>&A5b`@E
z9i_fS|MRQuVHwZw{%0T9<T!aD%UF+H-mvt>chP~?OvokdaBF<z+giB8_PV)j9FO$N
zIli(0dhNg+ihKQ5BDYZA3g8{kf7^zv68dM@{+jn~013{2@#F?~o<-QYrJHl@_4rpz
z&KG0*qa~*8X}!|?e%*U*DfFzPYgC!Ju*a%xQHEOD{(0n^&F0M#`uZibs#Ae`l=u4J
zF)G8tSKU;1lbp|3tV<&L+{j^O_SOB5a^ruoj8b=@SpyTx#*dN@;RH<i_ZMl6H~g{>
zblxq9r8oz0g@odYphkj;WD7{W$mB9k!}{dCfJPUyoEO+!y{ZV+8d@HxqR7#{w4v3&
z#bCTh?tnui6@G%5sj(>gi9zy*py81#WT#fFSp#KF1b>8hbOg+nplP$S!3;of|IkoQ
zQIQAI+NXEcCa5<rsm&$KdWo~Z;6T(1pwnBBGKX+@Su?HWLxeB1<hmiqxRE3Sr4?uP
zqFN?m1W{T+XT_+eAH=f~kSEpXO;WkjF6B^*sZnFlWyc{ef*PWN7D9?yB;uXr4zX%U
zE0-->1_6bDFgO#KckKA^x>1ws6;=kpB?kqt?RftagUcPb=!A%ulaqUGRO{RQC2kRy
zR_=0Q=fK}gKy=v&c>*d?8=jb+dg*VkN)0Lia4YSo=0TY+b_V5}_IfTW>u`HnXc;gh
z@*U15gHde)TVY=lkt9)|tG+R3!_&5cs^Lwy#^RCt{}_s&QGK!(;yr}<rTG5PwiyzJ
zCiQ~q7N`W`iH1NUuiUW1*~5bh{608Jx*OStb#!#XCU@Z3AZ%uR{OC@i9{?`6F=*50
zWsDD6^|(HNzMBFz|2qIPoFJRd)<@meK@K4dq)EoaEpRs$$XBEWLB5JlNzv>4^n}-_
zX6=?OTfhU!L#8KXdtROkp$?4ec#-`V)WFt3HPu)3oQ~At@K*5Zf1)^JaT1;8W?3_x
zkYaVAovWNZs|2GAqWlElJY_i*RnEtcE9vOy@FHOCm#9D-1`?1Tbj0apol$x+8H~h8
zA{(R=IT%WaQvxb=OZr%2E25~|j~wVPMCvhwz61poON1-BS8)M&Fex1!R@z<4T-_ZI
zhk}KyS34t+4%F&}5_TU{h6Fx{_-p_Sh>$_*Kzt$bseoz{15}TJ0Vr$|N2?jkCrP_6
zIF%wj4d&cVMW5Ur`(n=IabtP853t6<lVFS>>p^W>f+b`J^Y#=q!2Nya4@ymuy4UlF
z%OzpLk8p(AzsI_hw<nzb4rre^MV^(_nq0Z68-*@y+Re_s6fkj1Wde{7ejv6I&*oNn
z2Iq5u4FFtCqTU+2(VlN9O^({-VaJPu58NZWhTjGuoVRpz6ac9aMI>CpTX%MP0s`sm
z)0u*eRq;dm>p!w^hm;K1;*E(MNGc$(O$i`<$?_uK(Th6T`;L(~)D_eoEz*IzNE{u+
z5Ru_vhgh&l;4%Z~#dih~{eT>iqh;!MH*}*C(~a|HIPgBmB*QH{Tsv)Qk9wLQ5@a5D
zGhkPxRMQLC;4D&{+VpQDV&wGr0Az+uFbj~X44fXc2VInuL;(bGJ_LUD)7vYCK!@3=
zV-HyWWWdF6G?>GMgb6^j)O7&9s}ZIqSqmZ^wiiE48!8pD?5*<yR3P4sGl5jQ$y<c3
ztm@DK;g5hvAReqyl9H0kf#b5Ps{GcmN#Er&JdM|SW7)M1i+TYIYBnio*|~PVZt*r=
z-utLbA3#e%Ztqw;RvWFr!mxEKDfhrfegFE#f}n5ErEsvIu3irm&{4#h*@lbE3e~^4
zS(8!N#u?Nu9@?le?I9|0au@fVOU**O09_nG)Y)F9$FP*azi}Oy*8JQ1C15S{5iWg4
z(vuPswXyA3%m7#jhKMb|qC*bn%=d~YUd~sf^Yfeqid*r+hbahjIsm%lf<f5CO)xbz
z)dWRhKT>su$i87>D@5j|EeO0!6d}k5ucZGung&<-LVt7iYZMXL4hIDVUqS34E~6;9
zM_lyO#NPw|8u%q{3hZJZvD2ie1xgIZvy;!h&#A%a{P^)U9PXpI`Y1_A90#58aG&y3
z)j5Ki+1YOq<-5Cj@3S*;a)2(7ppPb`r<{7Gd;xK1&$-mQF-lR8&E#?CNG+A@FdykI
zT(o!83Y+FYTFXPU0sM)u+Og@qSHInGP%8JYv|5$tX668>H16No8Sr^EN1>7N3p4YN
z4_XF<g!FRq+08gcuE6CmpVQ@LicT2UCb&E~c01#hEDQ;ql~HAe?vnURo`tl}3K5ns
z#%w*B@El|=;;YkzAaF`)A(|u<<-l>t>9_YRKVbZW-^5k;fxj!fEtJ`06O)p%tMYdK
z&i?Y#-qQYOqPEO>;MG{y-`IXj$eMBO`g@}vcb`c6mMN~xR`SkHVC9YNy@wXC?ldxr
zMV;VbE-UfR+SgEV$kUBGvXHq7K-7=7Ow(2Bp7%35+K+rQf8ZPx*eAk0V#w?M1#8(3
zpyXe(ds$^d4TGQIq>sYj;_rd#PovIVS#bY5_;&;KI}ECdLN~vN|52-7{lK@kNpV-Y
z68^fb_ro&#BpbbXZo=UH2}TJKgY&e8hP!E>ZIpBY<5*t4^k|$|gcUtGoC_;vbJr0n
zM#}%cFuPt__vXzTIOM1g<7~rM7Q>*>BD}>~`s!fY3S?ORbh#6KK3GbXjkM2vW5N67
z;%Lgo!EEt?L_&8OpfO3cryNRB2|Sxim_+@5Z=G~GIa+FwG*vonFrfhs5m?gD@CZzu
zMcW4&T(@JO4|l-61kl`yP&9CvY2(IQfJitJQLxIv+4d>n;t3+hTx#v>1J-fqtchpA
zv0&S=W4SW{;`nP^QeuFGPV1c*3PTq$nh|#xKC~8b?fM&%ZLJ$^Zvz~_OJo3Tmz$fL
z;h?1}7)Qc*Dv564H==BV(-cWGsL=yZtKh(h6Kq6FS2IZd_5eOQc%=pPXx!*694pDU
zkw^I+%04>i2hk=Gpn-vbp%e5yDhw9X?|?~(4pUZ;2&dkQu*(DxvJ*1rR>C|2MiCYM
zwIjZkIGFk}rtY9_=&zI)MMhi$it#wu0~U!p(DnDC;>n6_0`2xGLTWwHv5B`0h51Bx
zT;@8@oPR-6Z)}Iy@sRJaz^E}vfd?s#{-EU!2tDsXY;8Ywi}DKT2g_AFNhCs05$)It
z<i6W*fPy711AkGB=<Pdsn!Mw|D7+(4T*0=uZ`>;l6SJGAr%uhQ3s91R5mprwbfjj1
z&*(<W;f3DJtA7|yF#1DRc@c!|VQh*VfqFqwJ@aw*yP{5x2>!$-*a<BZRNWI~ZDN&!
zh07Ec<Vq{3FvP-wFD5Qh)TG*0-<0fsqbRIF8`cMk9Z9`#)?6SqUT_;9!AroVlGoVC
z2)s#wbRvuRSUgz=e25!?(rYVBHZT`tBUruy!a~I<WgkU~=JZO2DxK5#sLC<b1f2zs
z!9_-11eX9QZQR8HusSFsB{4A^%po-I+;?l7@7`TY0CD0)<SE`4cHJ*hC_oj#s>GE7
znS6{cAFRiv$qalDuVJ+(^5Z%Xn)pQ~s(01W9I7cdue_=%T0K3zN*+5qJM2&K;Cejd
z0z|~pYW|;RFBw02eXYA=3h6-Cfmn23IL$6(2PGIF=x~VXcDAPL{vQ)*1g&I<+KukP
zijk}V2-S~mfI6Ieo5^w9*K^&S{ruJAjRN@S!WzpTO$)b*I({9V!3`m<J<z<;uhMbL
z0FSxP5?d$*iA`6{3Vx$Re*ED#ASOA>b42HY#-)iwjU{lw{WV8kX`XXG2|9o-f79m8
z(l$1!2DJb`<2a8p;TecU%<;<6YQ()s(r0PNp`yFnkGZ<LhvCkyNbdXkW<Q)gqzY*V
zR+)wckEn_${DWwpA=D6liJ%f7aWKJ0fuh%KJ(FQSG2RjCRFh;#ha#SEY&yBFG?d6L
zYPg}6G!s{%#g}WKPkf;R{uTiQ9VU5UnjjSev39xL0pTjfvlPKI8h1k`SkMP3(*isJ
zd=%oKf7Tgkq+C9qF*|9Pe7Qjy_UKJ0;F;|E7l2ROZ}<f$nS3Ftc2rmtlx7=tDzcWF
z0Yu!v4<wFU9R4hDi}YNY6ch-N3eCjo-_<3BqHO%TzeaJgH6X&o;CC>%H-Nxe0Ue>S
zKwzYWx-B!k1#T7QP1pUnpSax^taEX3QHYY;ibCR&)e%3|9`W%*ld@j}NGg=v{QXBu
zZfZt`nAr3QOG}yHk>uoR!2=ghm^xe?d~1His`QqZY)ig0U)aC(Iy9{RaGl83gaDn-
zlQi+m|0%-#X94?5jO)_cB~@u;Y;1bPOq!I=tX`0|0_wJZpz6FeM-tDIP5<DmQ`vmL
z!cO~||A{0xHaXk>9~41_(o1gcd>apCDF;YaCHv{MDrPj^#NRiZy!R_fUW`CbL1msY
zIZS`iyn%dQa-zrYhJmWl9VFxrzlaBQwln8nvr56PTam_aAR)qPd7PKItkdt59?>=#
zR)5$nSAt~DKWlYqH~*Yjef9A~vL1K%*Is2~o?j%N4R>cbNE&mM3<R-FlKuaQY0<dh
z>be|hAm|x4@M~qV@!8656l~wnF#^gMSXB0bgK%gEY-B31#3u~zCC9)UJd|cdgcO`V
zKwez?QTDlS*!do6E>f3j!tjKB2o>Ev9YSzcq~OtXgm)=xEDA3lWTd6rw8;&W1F4Hh
zY4<=Rw5)R7&_+~6uaCK0Vs^QC^V5s70=tx>52GXj5L}H9;(gJCGKa}wn1-~Fpy`AF
zL@xUNu`xYdM+QMt3VaY05Ds1N9RT(cVgaGs421yQ&pDLw;}a94s|Ecd@azhp6ybXT
z>fk>Ki`L#Eh>5$;yyP;h-lHVrMtDkSQ?9pfFT42hel~bh1gJ&1h5NT{b4Jw!rwT35
zKB-&LR0FF$5q0qM2Zo0upb4IX(p=6>b|(MHQ9c?l#{?Px{OUj+G^%^;MjTu4=;BfH
zQ2ieP_qh`lV0L!4=cfI)knr}~jT+rry;T}8VF27H=r{_}tuu=2LAX}P!^OUM(S<L(
zJ_Q$HB(p8@A1MzI7I}0&tZnW(_o-$g3dMpRuq>Jt$^lnxJhD*a5f28^mcDz}MaRi5
z4)86<QEmZ?>?VW-vY7oq9v#JO5P+No*^gBt!=9*zD83fGGN@!n>74`S1Kc=Bne{S3
z{Cmp_h+@pMy8iR(ZF@;H#Tj~SP<aa|dcmhCc_u=6V8v?E?F6ugpxKu@gNz_{dhi8i
zrlwg)j*v8w8&_o^8%4vFhbRTgocr=u!O~Ds;xw<WHk-3b1uQ_)fIVv&AqwCg!;e|M
zX3a89uqI#A?fk(-gH9g43nTvnz$7I3Cc-c!&f>GZyu4N+B=hAB^N?-8+rjF+oPrO6
zGbkGlYD!DVet2nXYH9*{b5O2=z`vlUCjrpV50e%)$W3T1E`aZoG{q-Zq4lD&BJmcA
za~e!U#0EineV~1|-Qlh}AS6VhC@MHXNTo;>1f5ZGb92`sa{#lIB*);CT%Q@~YYHXI
zj`?@#U8iFuaX1XXL%@wmoMx~*J*?w5s`<q0djN_vO5h{Nj?pMepo=eS#yUVHR(x`F
zN#cy~)nQjSH`$8pklmL6_7Ug0pwp}{Nb@#iWc*~-m{3R!cqP57z0J*8#Eruyj^&in
z@I4pJC}`@8v-qvElPHt6tzH7DSGqUCAfpQ)2)4`}4JJ`yu`%t)OeALs;{94%kAXKa
zwYH9eEuRvpP@H?IGIAAOK^u$JQ=j4ucAZPFlmVU*d1M-yB|9|Velmbl16T54@+KfL
zz+pWca6H_}2uT`T+4XuF*rS;>59dPBuE2<EMdV?eU}DUH8V0nU3+SbkkPF3`xl6;B
zstO%2CtsdBKpbiK0NElY5qn9T=ZCxo>+tdN)!UTL_N09zCIRt9+MJH)#e+IiY^k6S
z3(!UmGy<T9pP!$Bt&NQ!n7}X)Vgw%Hoy=gQBLW*B9gYASO#QkJj{pGhja;~6YAKgx
zAz>V_ALjzp2^Mh(#3KEM+aT|k662EnWLFd<FZ4n*%}p~xzasK8xOoG$WbK00m3EpJ
zFJ64Wv9=?LgbGF039V-+---H@$V`iS5kf-Qc>gyYs#3+aB7bl6Y7vhovFL!D+k|{h
zA?<0{`RR#{P(tK?`g9U?Lms597zjgfEDb>=AOs71ap=b@Br*p=XsZ1L4?;zLY3Ut^
zfCcZII5;@?O&W_|UC0px#X_892(Qqk6hYF#W_B|?oCUpE-#`Nq{tO#~2CzpF&nGol
zVWuLE3wXOtK^AW0R4+z&knPJJvdz!9<LTK3D0MKMXvk6z+K%$!t09=@z55BA5lNFi
z9PxLO#zK%NQU4oFV=W`29NGYIXI`5$g{%=7cP0&esHVU#Z|IwS6da6}offcsgulgw
zT(@y!K4`2DA%}!kuU@?eQViZ5%{yX*k3eQX(uqL6D;#7bZ5hM|4PR^k+--N!mgoWt
z-GTt|d!Z#mz*cF{Oo_7=F%*hgp^n=;kXyZ5dtKkh3?NLxvk<2Sf#sE_evlR$*qlA-
zxv%5rMM%D4E_+Ag=<T?EZ+DCadP4o5d#rDroLomUz*$}{^=_>I-!FgA-jckTUFv6E
zmX_AOikJGTV&F@43RMr56o&XGUDd~+cYQ;F8u`XOvh+nPuP^&fX*iN4>mDDi8dTMK
z64>Su<J<kFUu)A#jZC@pt0U?)`KZGXYcnEU32F$DHh(f1#<4@H?jB4~xUX~X`O7o}
zIq(w(53;^F=`cDmxMJtY$633Vu*8KTkb()4n^!BuS|rV%{Ag_*s+iIa!Atoqny>V)
zo!OyW;I)M=>ZC(|^8yeoS||&_AMUHYPAUo?&)v2AB1yDBPVIn7DbUcVP9CJ~6dQgT
z4PFjCm=A-`yQkfK@nY4>eRA{OC4z?vKCeDf@mOcCGJJgQFN_ncb`Bmby`#G6%a?g$
zk&hS`y_Tz+R7Gz++l>?Erw-WkHwzX)q#z)jP>y@mUQ0g65?cq82&@ak4(oNdY%zp!
zIqY1e&o2e&$0>6!H|}RA{aB^UpS%TWEm(v;4{}`2zqNb<J-TpRfTR|nW!J31_J2o)
zC$Nxk>_&+(VC|Thb=7T;c7b0bi2_x24t$gV4(JdqZ}XHTFU<3bmF}5%xDR#@4kI<#
z0D|<iE?y*_kt<B|J}aq>Qu~xUkV37S93((75ULKJ*p6!r6WlfAvXf~xW_2khp$nh5
z=a%K?A51zXX%>HA*Oy@ySjj%}#aL$he3*;p5fR!GxE%GxQ{1@Wz9!Mqx2S^#TD?UH
zk)=a*5&)Won_er`qT^Z~-Sc0-orSrj$<l!vwzT!?8sz+~n<+TwE1?{B{+&2dQOo&`
z-rf>i@OyPnKkWXq@xs^T59sQ_seD}hHr^9i9RU9pu3~|zH8Lnf`Fm_!KDn;{ifP-V
zcvo%a-3FWm4j^z}BtkZzgbN@<OZW4r#YA2E;N;&%Qw0Uv6!qccSYMf5sKc#$_sH3T
z217C_Jnu@(a`-(>p(gTMU2Sc=emOG<ji|an6y$=hC%y_q{QIs7^IP#4j|lr$8@P_A
z_`+Q>q|9K=W3|2W1GUr#$Pd!F^Si3$+jcYw94^6I@H9q<3D5s=*6!fRHE2me`2HNL
zdJnJa3r;z41m-_j-w)L;+%SLicNV%_0vm4trb0T`_XobU26hWn#@`I<J3yrqTP|r8
z0(h}Eo=VyPOi0Zr4F72<NKbsV)&;!J=+6eB>???QX5uQ9z6eS*8#j)sQB`@Cf=hwu
z6g5x1X<fsYPL7Ww%Z$9|2i-y1ywTX3VXhgoeRRRn!AVr{|1{vaE|DJ0Q--xU3t0i}
z3p|d~HiYPh`3vu#4-E<5TJhRIiP$5siAv1vbntCI0gyrS*)`-5wEAq_xbK|4TBcqZ
zqsU|@i}0aCqz?>#o~Oyx+}BqIUWVKSSWB`hCsIKOg~2dpV{2QEoa7%8Hu}GEn6x%z
zAfLll`T)k$04-{2YWoW`z3uJdV7jjt!Fr?L@Rko7`yLbpa?yU9eoe?#q0wW!@eZkP
z-VmSnr7tf@k0a?I!qo$c^+NDM^PwDIG>m^i20<Y0E2l`sGZ@S29StMKLy}s+odxYR
zsfbvC`nUu5m%ub^bi$>oUDMOkzI$u@-2i~WqA9~PL3k@|ZPM2J5Egx+xZ`ILX#y5p
zE?`@<A-^XF7o7_*{F4Vk+nDI$#fvFinpqS=3XwZ+X~~P+8iC4X8YV|hPtp-aQV4N7
zg9+zCeGmTYBha8NVl9&NcCe4|z}Tc{pnyj&AP1;JJP|i!OA08d$&Y;{c#Q=rsixau
zj3k=gaQ7E)I9WIhnNa_*;@fXzJ3|{JswO^`{4m_{L|`TKM;8H2+M;Ji;{X$mv((&g
z@Q8x0;N4HOP<7ms7g>;nDh!cnI;GQh2b>4EP37ooM4(xE7$GbG&S8M53y6r&mU-|3
zgyP8u1_zi&qx%A|Pdz<7q`QCu=o|*N0{w-WdU^%0C=gH!f>h-!hcNwlw7H@MY2jgz
zk+t#K%Lp}^le5T~P)_KV;Yf8rlLDGX7UK#MPY!TWJj_6_w+vPo(5;A1NYJW#ZP13s
zE@xcl@~0>0NVx$<>D~)(#MjoJKUZfV)}o4BhHrg}=8UY$1Emm^bWsJ(yT#gEeC>aT
z;$;B;4mMuFU$H|yqM#+MIZ2d0s}|NtQBgulL!yL}<VMV4cQ?1~tgMSkr<gJL(xB#O
z6XZr!bY3+!Hp0L82<4y;^e9bZ;}Qr<DE@dH5S5BwpNG9hwy7Xv8A@56y@@F)9oWSc
z?dTIRK7IG9t*zNmyDX0Dx;b6pf~u-2WzB{6_nzHobMO@NfhimQu^NMQC{OoyN1+Ii
zs*59)xlG*f@+yFIO+&*IKn1|8?83sqp^lSoh_w~qso`-2^(Yk_#`UxT?j7PeL-~N_
zF2ZP|@gq_qy{?XZZv$TNBpPN(bcKN%gAbNMsk{JWPZ(3+q@cR|jh!ocId-x<DKlYO
zzkZRkmzQi<vNs}9Vlg_IdXlm=B^5*6dRe&X#5Z~6vocYUz-{AuZZA2S{r#q(sk7i#
zmnnMj;)OwD+5zme9x4-}TLO)<8ouHr$CK2i@bJhSKh+Z*Qm#*6T%_%Tcw%)2@I&|h
z3svq-jEtqIjXLX+cB9e>N4bGo{ShFpX>-;BV${dGySEM4dlIS<F&K%0yKxj_5p?PJ
z&ZpUM%LM@-lI}~8>XdP$PYRh60VYs!$~9f`2ln~%%k%ZGr;!EHMyk)cHU3&^BynS7
zV-icrts;jLu5(oLieUIr$u2)ky4S#Tpf6H-)LDa6-RPDcK!XUWZg4D3-gb6l!wF%H
zT8Fe^pf{r!!wDW@pal$wi?*S7B@HR4`R{?wCSV^3ZyYhB5ZDD-1QoRcj{b&{Ry-SV
zS`pZa{E42DY&auiyG@!hFjnDFjOHFp6+jt8tZDEr=X*0Tb)-8XxR73d03y<?it6}V
zcejU!$BD33=}SzYt;4bX@UN|d1`jWBF&>g!NdTD>lUqo&w&~;UP^Y~ruO7#6IjA3H
zaoYI;KqOeuj07<<QR3XWbL0IvYsfbN`U^Cu8$b|Vykv<FT5=IWA+#QHj<Vi2j=3R3
zt0zqDkt0V4TZ&R*J&cBEcSAovZ;(mgy1$e)>t1I-;y_nfId9k@1VaqiID)`|Ds2sX
zc;Dd-=kDH*`sDr|RbQNFO>OOCgliQv)%0z->L)_@SMoowG9O{q*a=}9Uf(nr%%tjm
z5nZRn8@@M&y*94j2v#A{fOhT_Br8;it-zjgRU$0};i2{`B!abcebe$xiA=XG_xRXp
zd_K4Q3vYVq_R!Ja%<200SvrV$HV$tN{*p1j3~@|6bMk2;+&$1jp+Bd_rQ29u=8cm6
z>UyT=tXc;6V1FS9sg~VfpP?225p3zsetxuQ5|gUVAlib%r<ghFpWu4T+7m@MA%dgK
z>E=6rpZDMhCvz9Pr)NU|hE>{Q;HlCz#f{*9CzXki;rjFw!{5384?OdYtgWkS{?T%u
zaKWrp{=zXsSqwBM2<^$MR}kyjjX*&DW(!2m0Q!cz5{uyrK4?lDTgN6dF1mVo@f|SN
zQFz%U3A}mVP%$r;{#3O4G|W7|nb`DRt({+nIS8yhCFUzfH}ACii_tkH@FsJ{mr=<T
zX;~=0?2;hxHTd~HhIKx43je8Yx{99prNTz5(E8XAO||zA!<NsPX5RuId9^cnb#<hu
z%02NH`sQ5Q4#X=OseAuteRHQQ-7|bAnp8)Vep(<A0G|NLJ&2uoJFj{M$2vqVf$9lR
z@JmhAx>hl~YK{ZCJZ5hIG+w~w$92M-&W4aXUnRM!Jmx(gz1iz(o4Q&@Pfu{&cCv9U
z(j!W9f9WTd?H=o?&5>YoxCw3+4Rxf23}*(7e?$}{t)e9*tDM0rkQy0QU05~40O){v
z+Fho`{(HbS19!wHXo^H21xAFm)ghRlwEm+U0U}g@=NOTvj5K?YhF1*y;7)1)QU-Q}
zi+WAuMbd<ai<?zxumlzVUNmVS`QLy<$&IC;%it`tu&~fZU_#x$4!sFrl0JYKl<8iy
zaN#%tH*tR9M_q&&i9$v<5NwR%4EeMK(GW(0Oo@;mpUJ6bWj#ez1?mN?sU%u>NmDxp
zD1;$=k?4c9z;`>5flI_n1bGyXdI2<8amb+{I1Ciw)Wkd1ytC${V0OSZlg2dC^Gy1Z
z4Gj&!1CLY)>XwCg#l>-A4GytM-`9kPm;g&eCernFhe;F!$I0vUasTdGlYZp@bO@oD
z9mxcJEhH<<4`yk{sFg58Owu<8AWMP{BqE~!PyprI;UD2knuCt^3J3^?F7hH-cW_OS
zUkKDhT}WIig!Vx9=xRpc@rto_RnpMnwM9S|F_DxvczZL*<du_<2YkUAfTui+jC{bV
zhaTYkJ3br@cNrJZBuJ((;Il7q(fhtOna}HrBcGjMo<-IQhZz}C@+xN$he^^ef#uDC
zD+(<7|74`TOhM@<28Xk$nOQc96)>n~v(vUH^Is*)rLxEUe^{cwW?&uxQ0+pbDgrzK
z@l?<+g7QB5<HwJ&y}&TUIz53*gRvTGDIh5XdYQICIwx*oG8k!6V6&I~U?E5FA-jzr
zD|AbP3rUF>Dk@4i9x|kd_8B340h`G@fk`7&3|PCRk3k>oQF-MI0UbQ83msF09^o31
zZ75u(&4*#$&qBen^K5c#j4XgM>KV#oSkDj?2B6a|l=p7J*2$6@1*ZvZQZmEy;k;F<
zislrM8A=dhf5w%GLP0U_I7WvJ8mD1Q=dF)~ZxYmNUcJWu1#s%YQJ<wOwh)yfe1@%y
zhcJeVf45|MT3V{@P-N}SpDKtdAPNIVGyoN0$u6lAK0CdDq}kUmVIcsz_9v6Ez&3(;
z6NlVS2u930&;d(}RJ#tjvT_vHbboglSa*!(VhvC_YAaHN5(0{LWw$`1O^$K|`+W(w
zb!=D=o38t$Q_V+tt3o<F1w<JFg2XDHM8F`u%`C>r$x>8tI9R0D09r)6Ns|b%k0D~I
zK$d~2BMe=Uk;y1o1RR)}97C8^IQVp=c*6&eu6XuFN9`{hpC#;v&T6N)8ISdJIU#sJ
z3@5FaQ)7L4Ah&g+W){GUx*@78Lfv!JK4j^QY@>+DTCJ($Gh4jGQM&x|pkEQY0t5sc
ze;ZD~a)@3SFmMR4`dU<;43q^y456vzhhv_*;m(g*Egryc0ILDacY>askJ^iLl3}gd
zFi8P4{ym(hpo~VFRxh2R)(QGQ8SR3T0fXDX3F|7YfEf11X)dEHDJUqY_N%-zj>3XD
z0Uoe)IXKzG5QtKA>0`vYY1EsrpNPsm31kQ<8^VQuj2&B%Y;9pdJe9gdr2Ps|yVbLw
z45<_5L>z?6mxh)$4}54A>RX({xUTC@0N5)3()AwMwEzhF`~QN2j?!l&JRvY28ny=!
zJ`&JKioRkaH76K(5fhdPA97$6>KjGcXv0B-j`YDuCxKAk2<9Z#0+;v0b;kv%1m(T)
zuKrzTUKSJiAK|%VC0h4Vd@&OZ&G3(O$}9jD?cs?at!Shj1w9<IW0`YoH5phf9F$wY
zMi#K>k;YN1J-)|UhI`(z#d=D9<_iuM0wvdl_lrqCG<>(n#M=pJg9n3wE)efbSO!Q$
zAAl}NoI^0qs-(I}6gQ&AW2q%UT9ast6b7WPfXf52rKJ5v<V_@6Q~YeyBw|qi=`r^U
z&(8nC1fEhd&H-(^F!${@X%xm{9YcE!oVig%b9`f-_c;TX+<s={3-Qh1fTO8S2B;nW
zHt!hXJR#y5V$f5Whdf!8NBP*<^Lv<|wINdM25~O~LnKK*&~ESVP+-m;g<Mx0DjJG>
zP!5Mrf?ioE=3Nybw>-oA1TZ6tK)if&q6YAagWHn{;M$HBT?Hg)(liMHh0QP%fFcXp
zDfTb3V)S?afR2}xnEIMOw-2<IHpqMYHtfALmj?d(a~mw{&j`mrM;^b3^B7w|I{$9o
zzI~5VBjfXG2{3ef?xKD3C0<H*%}Q5!M2LhwYeY!G=^!5u{e0KQZZ~fS7>zkO<Bc@<
zpl<s#2O==<p+G(|(Moc3DkRyYsd3o#3<)gbXvS<thf2^d;FP=jl!^Q=KmOW(AIV7i
z)BfZ@XroPSbDIh<pz+ZoD6*uMdpGF(NKkQu?&wv}(i;A{iN-CIG#>nH^m?x;*(6Ve
z0eXKlDZKZvn5Uj;eHQ=2+BfE%<bkGQ(w(3ad+s=^ZKoFLc>AlKWB~B?+M0;D%#?qk
z-gTv?=oH;P6rqurmlM4ZF<ajohX4As+>$Cy*KehdmhC!yob?E?7W|37WpzWZ#h_I8
zGaNKDA^dury$9<Kclx=`cYlZ}9-a(km|qry|9f)>UT(vcksqg^I0gT*P;Q2QLGd%{
zB$#sSe)l5Z_ybK(1|yD_quqcIis(v$iUR2~!D)`nn}i0xKgq#S73gCVrtbk`WmQ(*
z!|hp1Pw!f;&zt0g+q;~anv8S8p`=;AeyAdVObP;jhnBV{un&<@BZ!UWh%^*TVKD`8
zgrtn7_{E6*BoqT81n?Pdgi-Yg>1by-P_cn33o@$#4E*Zq>SX33igPjvt@0`i31}=R
z(XzEtMg0d@$^qnn$04)Lh=&cICDT^`QIX7B1h%Iz2w72sCL%x>L*F3LlePgV5jk8j
z-&r&p<>NCT_0xgN(?h{p45K$d7mq<jgxFX-m`5-X=qHFoWlkD^V8N}tdLugv=5Lim
z-Bn=z^6DnP-zJ_75-D*@uK}QOBX*J5DbP%{t1koclgU27Fk~(Z5jN4dgdY`-&%~@s
zUnpNooCz^RByNyyct6sTi^A~&8bsVmX`4YQFkp@+WH&Mh0a7Y1*y50l30R!ZaT=kp
zPj5t10+|MiR|ILUgEls_JNd!)$7&Et-jus0(u(q+4RjG17J<Pp%`Gk05n2)9K^|km
z%)@9A;xuukVF7Fn1GfVu@(w5t5YKc<L4fwKw*_{ll7^5oag2b&%d%h=1{Vm;U90*f
zA!TD#Xq*X#1MVmOg9M$zqsYQ!C@19R{DJ~v!Xz0Q>XU(cy*@7>UMR8u!OizVEN>%v
zjU%M)!LPmeG156{nQ%s~(9+Ypjjk!65S&TKUq=wM0ZgADj*=kM-`_8mNk`t$OkZqd
z6Y_Kf%%g<qL#Z+V*_I<le-S_x2=<S|bwE8q0w(yB3u+JUGt)i>v?a?Cmoe!M#0|=&
z2$^@SUL9$+lWo$&<Q0T{A53YQ_w3<RQy)eY$NTZsizI(=$e=j-;0qqQD^r#&TSmNO
zCTF1plX)GGa>-R9)CcMvKuor)PV-M0ebS*68hZ^KA-_wDGLb1yAo#rc`Q`*&LqieC
zt!HKG;FNf95r|!i8w8~%$cP~T7qEi?JQr8Oo|b)LY$nWLNm=PB2a)QIDL1rgZ`D&p
z5>lt18iIHA12VY`yf|E&y@<~a5jSY1K8e68=-x3K?o<G3kN_DgOGmKt9TZ0m%EJw0
z9H0m<FRvUEVTtS<P=k<RTZsw<5r8O~;Pi-X6Cw}kP9lAoAhuig@~<cE9-PU5y+Sbc
zQ-C)YLFOpk(*)B?#^5Xk3|ko>4{<&a^#HDaO^7t)grWCzE@~cT&y+J%>HY2@z@|&!
zg4m)l^FMkBy1v9Qkx_Yn?jd*#Tt`g3NZ?!`hvzojLuV)u0|8uQz9Wt+nW%>Nrtzi;
zfu$0?kEjZXO_)sTM3G8pMdj!R@YLg)64wXj=Akl?A6$MZ*{C+v{QF7_JY4g;!vL))
z6(~sI5h6uAcvdn;%FlwV?ywZgvohE8=1!21QBaP6S2m-~<c~%HkgDs@jzQ+8ARseF
zdH;b&a)D&Y98%yB$L|3Ex&ffQf&bAIbQcc|7B0_u!6HGJKhb_0_t^v<f(eW^BIY6-
z5gj-ga4eSLR+N0!g-sG=1F=Y79s5}VYp5i=l)kS+!Lk#3CG3ot{ICoZAI`4}(l$|^
z5SvxNlmpl}JrySE+)M(`tp8AfRwP0iGy)*9o1a&+<)qHb>H;M7`ien52K978EH_h3
zB6HfY!ocOl3qCoy+KTh)1BE-@=-wCpHuC+)f3z&NM@NS3J)4Z-rJv}MNf#)j6<b+i
zCwEm@4NI&(Y$;NgG%!f*mtc<hIpb^Q|2pFQE@dTHw`<8Dta*<-tb)7}e`C-i4TT2D
z$^5Br1)t78?><}g-uMb;-*}R>{|q8l{sIxjn`op0{vJdeeg7tZo;dqJ_5TBiknV_~
z@)Kh{gsz8w=?d8C7xio6h;ppEWMCv|tFQN2Gk$5H6!;)FEVa$7?OydM^zx8#J_dn*
z)#WIqiE#7Zbvahq5T1;IA-H)G3<W~Yx^ut1`KZw3UwLKDw?NLwo3VqLowqnf7{jMu
zOz4;$%(w-GAC#jrt|MoVN(0BF@bYg<qf|XgWOQji-SDd&gy+!1AGBnM9VBRMPhqM4
z=kSf7P;<@o#rPJ$CqpQxRLsOh-xng7p4!-S%pB@g!dQdLpYPLxHm|Ayksrra35}F6
zFy$cPB6Rqu2BDXrGSkTk6FbOQCGg4|yu6=ZH~y`s@PNzh+lWX^XcZXf?<Z*p9>}cE
zbAJe{6l9^nJUR{1i3a8DI8>jB77tDs^A>U?ZNcRQcyjyLdYrfuU4>7$Tw3^mQ-id8
z)u2lf7rPy9={ri!3%|az_9kXvc*XECo1mhBR^v8YPfz~=UcgNlr36iZIEHaa0;)xA
z`m=a7uE0dR=WH@H95rgmMh2%{FT?5xZi(~~5x*S#-9!+ultWWuGfFJDZ-S9|Lx`&$
z#WA|1vH&E|Z6^ZU0M{WVbEY9_`GSE?K&#%;HH^i;2dJ)AIma}>yNw0{{jfnB1!{7V
z$`qdjQh=kN2p&ZVLneO1;6nzNo7EYE&jN!-WF&B<vT)#GB&w@HI;NlF8WZXdT@EMV
zb;6I3L2XzviP^6E;E{{OWB}4oK>Dx_*;!>wv~N)oLMkP;NkE5am3U^%wSfVOwfq1G
zBscsUJb*`t0)jUobGk84N>ES`LqxqX77f^MDH+s)0*Mh4Ajw=nhPjyjd<<#ZIpz_v
z0v`HL`(vTJz8SXt(Sy*V%;di0R94Pn_#Hkm-~r}1KFs)2Q=;)1%ymK-UX}&s5FUpJ
z=r_8?WIEoZMJLgyh<Gg%x0QjxX0S~v%mNsbF4SRk6JT>VLM(x>ScAKub#3aWCME_T
zMJJ*c3~a&y#B;O-BZcrbj=B}H#QZY0K0V5}V8E+C&pO@*;sP{T-6FWLOR5V}dJ~Po
z#i99BGI-}A3bu>SArwA6F>$6$g1(@Dy@El&ajI8f<6gB~l&Y|Po7hbCrj*oSyf`rd
zqjAFob+R)^QQ|W}SugWyF1O9+K0S&0+LbYLbJ5rtPz40DS0?C1Er-d~N7TuYwBsZ<
zBpRb@wG;#e{H0{dD`v$INJ++qfzJ%sV<rMn1;lPKF?bQ8A4E`U46`V}d{aQ4g>z?=
z7m*<@xQ>KUC4DwXM}!LmsVCk4lfqfV!aaX~auuIUGC3fp5f3Oa`w<%;y!~8OJt~R(
zI1m?rG(hz}06D=0t282xu3FRIwGUSMjm(__Kmsi!NM_(;I3WiXe(|zpL(SQXDwSOz
zT>hRPAOrKjtE8lhkeA@@dk7#<iMABj6bkXLvNNc2`~aL0=>{r<*R6-q+f{N8?Xx)r
zc(ftuu7I9NcnSc~a_}~ZARu3VBNHuw=6EqVJ9BO}2wM|SE%d7oFgQ4v%yol#su}l>
z^y#4rVmliP?)xcVF3`yh5ZUopM=oVd{@9IRw&pMb3h@HtCs0Vq0d<Y^c)~z%f{dPP
z%1E!(HwAa0nqhwc#f+RXBd5m^vbPWX6s&Fid4IJP$kbK7#_)|lQw7@U8An#4r4Ew@
zg7R|j`Tnxz-~8hLJkf&R$Y`Cw>1Y3#+V%E_=vETcK<PMK2!iPXZsgD}8+@=BADqxW
zw3S$C|E<4I%-3yYmE|^II@00vs~17)bYS?uH7xvt2|!k_;QeDrfk%sP0e8}|wKP&2
zNkwg8Rs0d%5JZ;AgSE=lt$gSl{#yj3g|4yTodP{|*ObBbKPKnwe55DisQ{5F!uFq%
zm-as-ubs?;yZ+}vIYvemb4_RA{5n$<NfjU_=Ic*D0=#X$b=%YUKUO9DYKJ(S2Wub?
z(ZT-I#&`V>yB2x1Lb1P4xf)ryaGq!i*ZxtL|IMoW=NDYs+&=Hm;i5n@1z8(mE=EFj
zA$lH28v65p?IKbM1QHJVQiO6+%OM#c^j!e3Cu#;fBo#R5jHop`MKC2p8eBFhV-O|C
ze+7a32Ms`ZQ&6CiW-ggIw5bFVD=(&eC^6x@<&>4JL4!DHGJvQ44Nh!A$NUg5^aooS
zp$;YjJFx2C4gnJz`vTDld{zNWq~qUiGZAAyoW>o%%KS-W4i%VgUARGG&!*hjqnZHM
zlXtm(t|k`=YxuEQsA^Q<BOp^lKHS~D(<cM(A7QpjxiTL3ftadMHjwG?FqTuJtb(Ul
z3Ee-Wl0gOZC^`eLE(v~%_@_bEJ;wDTzE?zW^gL`*dItiX%e+mJfDDr9z^SI9rI~QZ
zD9~`h?m|w7)J{fuAr*&1UD!Fi8jm2Uri*z3k{@@TOMTTfg$JjQl<|+MGB`Sej7SE5
zFo9PVgvj&TSPm~hk>wB3)5wJ~O^6m0d8!)xhb_nq6mf6H5_B^}V=^?PiU@G-alzr_
zWi>V{$QBqGx6W?WGM>3~dm6<WF^V8J`m#u@#&pV$Anu5;9h?jZ<(^oq&%2PwBaX8Z
zdI&$ak+czUctL=cFG<7)>R?i+pBRxuFmSCI3JDupu_%OehjT=UW|9Z?Nyr#%gyKM-
zN+sGZktIAafd=s)KPQKUO^LMT^NPDXW0mgt(1jg>JAWUD{#Ib2c9KjPS6wkT*8(R*
zYBew`m?u>N$o0E*d*`P4O(ZOu0%>am$Rhn>zr95WdxITiWym(`t8T-jNL&jKc}Piv
zMwT70TEKYB4A;=k;A>=c_)h2NhNRHOAO2(7%Hn?wfOU=kud{Oxt2tlWc$i@vW)IDb
zLrr@RlQAiW&P|coL&Xpmp`sC%R7i42A=%g@E7aKOKp7!9lpIouMrx76M9Xv#nJk1#
zr9_GL=ZW`vuXpeF-TS?^|7Naat>5qaeGd0?-}m#*`)kYM_(<mA2Jf8)|0@EnysjL2
zu$_jxb-z<v4#QP|rn}wC1RMel$$H26oqDL-4U8BC^*(ppks@oBlbKw}N#K3E_w4cW
z_kYjuz2>#;pYEtk148Wn0sh2l3-uM>z~+C(zK^szkM3b?ylPWu$k?S4cm6r{%}9^x
zn}E4V_`LlNqD?Lejdu1>D31MWH$_e}f~Vw`J`$F;{wE433i<y{AN?<ER*dXXqks;G
z8!#ZrCgGq`^nOr=fqXAZ%QIH)VxVFH9G_QQ+y`wZ)o2dT;w%SL<JuXhWMBKqI*9CT
z%e8mj8WBGtFo$0=p$0mO0*J+<Xg<tUW`aGa4yn*C5fhxO!^Vu;;wHF7Wfb%#ivv!9
zN&6q@u<fR{AQ`13`P1U`_)jjGr)JE!@8|fmz!&@tw9bGDsc;~<_{)$ooV0lIu))%p
zpQ#+CKeCvKzL;<E;f12fSNhW0`u5T53`AuG557;*2ocA2I_7*cw?C{(WqEnIin1gx
z0P`-;G`%oN_w)6X@%3r(7=a6y*rGh$?_xDx__w{xbi(ikGmRWP?MnK*d~FTgPZ%Tn
z;Y8%y0dN?Lqo-#@*c4-HSnPr)fo52C>)f=r1lAPOV^$F{m6Z2N@K$3C=F9kbR|WAp
zjDE-bp&$R1keQiT&+W7TFD`-;xJE+_t!Sm2o8>v9{)cC7VfG2AYObi5b;anZIj+S!
zC+9>&RLMB2_0GiIRySR!mNj@dgxM=vzD?ee|C`sTYnqr_@%I?cl$0<M(Qxy_2r0v9
z<qJ!)0+*><8XKEmpKu%UqM_Jp!i;2i_r}wcrsT<lNw*DSUk#xwjM2X-MP|vZudS>~
z9#>S%xpREZhI*cr#oDG)PZbYX=i<eSPDWimKRmaWROgLw{E}T#b50qVm=wxi5HEkt
zU6FODc)Ej1Jmq22XPVD!!aucNHqz92TbidG7?aFc$(+f}odAZZ^R~a7Hqg8P-Cn=D
zckU?psjaTBY29MGMe=M5OHiJitm)jN?`*VBiYxlzV-3Qq==YRx$SmU^sOD)Vg*rDk
z2Nf|8Q<6_jI(O+38+l-trX}mu($l#-nh{@p^;MYs__LDKi>DUxdR3&S*ly1npEt)w
zxeck8$FeG!cxD1lr8@d}#PY{GQZX=AK}usXnotix)N*2sS^g<;I}_2p4j(*rZs6lv
z*)ALDYa4h>Q}D-EpP-Sd`_-m)36>NAXJ|@#P)KiG`6IWFYQVValV8fpY%aW=wd=vJ
z=Ketx!-V1qO#$xHrZlv7e3bo^1M_Prp*@}cL>3HPHo<V(;ao_zxELAi%)iRhgSW}V
zUo_qO*K{0LH+WQb0o~YVU~!4eybgLid6;fH>^$Eq{cH0{kWwi=R3sp#tG2?Ng$aSw
zb|as3|B-@wyB>CnY;Nv8uHXgFgkI@05mKK(+219g#YP8_ikH_R*I?`~G0L#D+kT|m
zwA7CTvC{&ew4517T2`O+w8I&lt4ggphTon9%~I%sjD594--e42*5l{Lym)CnaAk5`
z;|3Ere+bJq(^1|$K4-Md@c47(>xPcwt~c<vJ~MLJA$(FQpvk8fOoRQGLzcbPqO6Uw
zx3eQ^hIe$;pZLQA9c^tYrcN|DQbftzT(kiUGj}>Z8W<5%b#iU<!#?fan0#WZpo5z=
zEk`%LKNF@NS8}0d3awin96hHHKA1uPKB|AKti8JQ!>g^Wf8Adh!&k(7|1TG24<C{V
zTv@j~?pbhi&?|O2h1v-`5x4f65r%*ah}piG_?jL>S1aM>Wj;l;g^v#OzZ?dM1lD?R
zTK#vAAk~NHFdmdqcFAy-#nW7<QcEnlj$aVRJF4Ve$ZQy*xJc3HPuaKg)rb*atOFrc
zJsH-tV!>O7c<qc$8#l_n2a>mtld;+pPe&0#8pPk|u5VuKN$V5BU2<Yfd-9>23&Wq^
zp9?-B<aIHy<AhQ-ZKTf>FheNk$+p4nk%lgh+5;{pha0UYq$VP^=<6T~UBDuplC3rI
z-eyEMd8>Ml>&QX-{Ymf-srNdGs*m58>kS(;5G+Qj2dK<iG6BL5SN2AMn|eL1b?y4@
zc`zlzdm@CWQ1SckS{Om<$~mQ}6EE?`U2RpQ9B8O=fN9;#9hXH}uNX{mHjhUrg)go6
zrEd?WrZ_dE9~_g+akvi(V7X_axcJaAA{&XPp$ms4UcAHAZQOP9BH;kA?+w+tUlE}~
zr^>E92Q7%>MR|~0L`4r|uD6bJH-)`X=ifBV6jO0Nvv+;NOOFhhybc%@-2X|&*|TR&
z=(f?yON_i6V{Ry;Fvh(CcD#6bbf;}Hn((bXR}ZeBLYse;jQeMLNzGkVX=&-y^b6{?
z8-k~Z#))s7PjHE7S^Z;#jdMUtpT*Ui=N;uNNFNRT;wRJAF&q#+-$gVOi-smMzd`D5
zc6XB@1kn1XT|5)3=In_E;YW@g^V$8aFY_yl?+(Y=2K_DGeI4UCnX3aLX=+SIeo^c)
z?8<N2+wo-~-1Wpe!ua#WS^~Kf8z=)0{&#FhX=<o~g#k^Y6u$t%X99y7VbkKDb^dwn
z#bBtCM&HA85w#IWrsa@KP$-UvAUS@wQ)r5OeSJa6X3y}4F$**kh|7aa!$2nm2V9g%
zdUFCt-#K2t7vG$-DHD5M>-97nKm}fcDnH-gVMO3x_CIoEhQK}`S%l<W3TG$-O(4Rq
z&T-p@jtZV2cEc<Rj9rk>dxuE|Wk*qUd2C%{6iS*3=4>Wg^uM37ENlh*VdOR;$9(R5
z8pyR!t(u%18Q}I)j3*xg>-v4APs)i}Juyx>a%ADzmewHG<j9uxC<#0URW_0(AQTy+
zK|LgkQl)q2nLNbVVXtgVdt>L|undJlpSQNHo(BG-I)v-DFi;2+i;Kng&fl$G>x%%=
z!rs9_m*X%;85%0f7B!s8FoKcgS_XJ3&{z%dos!pPiBo%~imT5LCHP^Utb#tS1B&Z4
zVs+C|KNQXOlx$nmx4SQ`v}Qu8p#M-ZkF%JS6>u}1W-(#&=FNVzqDj&7Bc4;?sJNBl
z2jdIle{Xw^N10RRA{ne^3dF1SJc<KZsZ=l;UbE4owXykos>mctCV^%ouEGFhlN##0
zFsZL(UBc-pX5$tl+b7&~K~JOM0%&T6jns2asL#uo@zl@phd5cT0BidulIoQjf{zl9
zCKLavqU+*UuRb?geYMhe?$Xn@3fvQny)!m#-mGgl_0a4uOy?`>8J4Oj4f9=Km1`JY
zPIz<7^`uIQjvjybgT-Bk-^$8nzMT9wWq(RIEAK*m1%-eT0lcyQlft~^wP}*bIn;|=
z;Z;nik(x(Aa#f17fQF_BmZPsc{p&4mEY7IMoXzxXW~MH5$pyXI>idP|$5#QWDiJf8
z6(u=ca$)m`g4i?U{%Dh=!1BzM1y*ZbElD_Y=FCmCT3vz;RzuV4Q&dUIr9>3gUOc)W
zHIV1!zHnk!>SFrD#aNr2N7+%RB1G%r6ss`n+atw1<(0lUSHP>Wu5LIF+T?<*`l_F~
zj(gmZfqyLC|0qz3N;)H@9H!}qr{<T?4>`Sdp-Lt$&3Iawax<#Y?Gx}s;hTn05v!Pl
z_3cAyPb?s5>n^-?Xpa2umgeSuxD-b3`_`pjSW>`G*3yrJfAD|yO)?VU&;M`L=jDYr
z(tKvhV$U24kbAHb8aN~8x#dUNp3>^(G1iobnYk7qgrP|E$l_L4fO(mZ^zJ>s=xuWf
zuUy6sfV;Uc2sDjij3~xlNIsZNxAVYigWD9qU0qc)=_}M0@O}girWTjG=NvF-j8Uvl
z`{vR~FYr`_=+7vmUyi7g#ErIV*9ubdPDr4xEqW{qk=pUxTgHnbjV3b)$%>g}Owk^|
zQSfO6dK1jr1cE>UB%OpHr($x*n7bQR0BQ@a=p%$g7Z6PHuT4fBF4_)4x))p{5Kb9f
z=0|J|8OU5}z})^Q`F7s!Kkp;F5<Lj3@G~M1&x1!koo6`p9#%ZSA&Ru4lu0s7r#2Dq
z7gjIW!9u0L(x;G@%uOX1bvv67!K^iwDDA|*OV;l43!w00hPnXn*v3mrjuQR;P|~dj
zGCp}$;4cHm+YU%_6vtbm+=j%rK@7ry|Apek7)H#Z@JA+O6NyO^RAt8Um?54p2Hy?%
z9D5qE>X#ykBiLgYr~|Q-u1oBBzce!H0jmT=cAoWtR{S6GbQ7^(CWU*T_&|KufwUm+
zm(O`^Y4g3dx3XUk8mSSp3Ao%e8Mz>8hoD8E+7Z<<O7xif0f50Lg%QTEMZ9vk+p)(!
zd8g>x2~Ub3B?O3E?@vXIA4jAX+cv5KwpGQtRvYwB>v{UbiH>m-^<?@?2C+1pqBzHI
z$7b$CK>b|V5T(U%w1DwFi;Y5D!@G&92|gXw<;PSelWw|=nKeiN$KH#?g%E8$C<(1-
zU)ho(>gjfRu{aKbK1mfQD?j=BGO*!@beuHF7)n?iam<7*L2y|{lhUIxk)ir9FLQ@}
zBM>~JJ>+=i7t*1o;HKt)x8VqBk2!<;_(3EtPO)IbepqTzDCfa%!=2R}@E;rB<~3k^
zLdNDS83W+6mt%2J8(l<cR-h>*x&k4MVE&xa=+NV!{5NPE@wE`eA1C`EbY214xoCaP
zC$gMVkKj1y{lX0rJL_i8=IZU(#aot$+qi-Pacyh811#=!IFC?FbeK(=va+$c)GsKg
zsLP+$e8-W^e$#|Pkt0`8QPIoyHEOXscqAIqvQb8eOGlQ9_DY@2JbE^5HhvabBFvYg
z6cQqvT*NVfgG~hWT%cj44!`slxyl4-aV8QoJ~Fb)%u#yrm_iShEl1QMvORWqO$q@5
z;H~w5pX<z-CsEXj3JT$vT-G^!P#ju1t>d7`c#H}_OMH>|w7M{WPkYDHz2k%xN6)QJ
z{?SI(YH6`i6CvWy-euw}3CU27i;$!!S)>*q)wB!h#9o8XxQnnG`*}lwHT@usx$KS6
zVmZz_E|~1jMdz}k<YL5LlJX_jM|fFqo5WmmLTxZ=2`Gxgstx@IUj`D;5<U2=vteUb
zCCId(`=e*i77zZegHuIsghV`HD(C~81&)ULn^_DK4W=LME7b0GFJ&rhUfmKD%#=lZ
z1XB#Lz&vvo1(VVzOm&0P#X8TX)95;>eawbjjW$g*n6-|v(0irbwH9n8!o7oza>HVL
zX3|q20rPs=CX5Wa2(i|BPK2_N5+>|BRV6hX)Rix29OJO$5Q-Mc!K>72ujr>8YvxY6
znSHIHMp*t>-d#mEJestIw~_IW4<1xkFIwPfrjvR)sNQ9AwcmEV18J$Lv|##!hlV$P
zFB=1T8=cPxscZbKffK)lbI8}*yLYcu8Lakx(k7Wes1<fUQUkH>Ay|~ioa}HHO7w;M
z?q8uk+MUjXC`75`yHYZ`#$LWWmj7|Bo9{YM*iK7O%c)Pi8rpf4_=-@`)-~n`wIX-5
zZlY)R9M6$~&o>ex<a-?kEcSc@@Fn{M>w;@v6YDiKhW^bBmt=!3gZ5679MWnao^Z*T
z3LiwKcF<ph<uo$o=M{P7Er+p>Js7-Q&!#EIhqA$*JM3O!uRjFjkxd&Emmfp>M=$T|
z-(ov`Q7>~Qb@Cdqk|7j^CiOk$mhs%M)`kUbB1>%FgFOKAp^gk%WtZ#cM=TfL(c&KE
zpQ<ihZ&^f2MWfmA7r5(ytGTPs+Ws7V1(fWs5D!4W9pPzRFM@L(O8NOI+CyF6tT}_@
z6pGd5Tr4Sj1-KaQzK$4u99KRuc@f(|8m_wKAFKj{CMj(c;32aH=GVG&SOg|70b;_N
z!d>X&NqyH+NhNxrFrcg4wzAv$u`_^uS!*(t+b_grQOt^1Ge!Imp-ZT*Kc%QqLN~zO
zFF9%K8(=hcE%|3Tmkm;p^RL_MuB<Nk^YZ15-M8MO6VrzF#y>qfZ4F}wt@&p{tk=9c
zUiwiL&=hi@Q14v!6@~5|xjK?sI_5cms2R6b6eyu9+a%%<k~QcUp<k9&AAzSMS7mwP
z28iU7Ap=_ViM^oSw}z}u9_#<><GKc#bYUB?T$Zb)I+X=;O2)S+bn^^aD!eD3!#t3B
zXkpBTG6t!#jR=UqvCox}x=z(2ohioKa-zl*YKO7;C+llLSok>GPG$i^)yIWSR00Kv
zR!6pc0QPKrw>?)N3y{Q)ERDIqh(N5*=;k$GD+Ho092gv&W_f4xI)uqB>4$?STcd^d
z0T<)bJ7QdoDPIH33tZM$h<Y1}C)OkTNOqzGJ($LbT-4t@VvGvJ@Q=5g?rpn}xGDZN
z)WHe(Gq7Pbn)Wlwepoy_=8t)a7u!JT11jSq4V|}98%U%B$yv|PoshDh3678n3Fl(5
z$33D6Fc(94c;Z`DrNAl`%LqIqXEQ4nE+$D|yJt_~V#=Y>vtIuDo|WZd5YLP@T6}J)
za&JICa~cH`L1woQ59^uwJf}Y+$6VpuUgTKF5QrV$TTF+H)*r%1bHMW$HwX|U@Jp`c
zM04k%Q`t?RqUVvj3VBMDI%4im)=(eYj=l`X*{;l>H2f7Yf0HRP-h0o19I^{Pv=)Oq
za+v5}WWgK)-ootQwmyp$9v-qfTxu&hXT*B>%a~(*`Kv*z<OuMWI=r2G>FGHF;`Fm#
ze#pDrho&0F=!a4=p{^pX3qL^0AO6qopcHn;qIpkA@m*hU&iq?$$)4^KWC77+T1RnH
z$$KLYJJB@@3q-BgO<RGPk!&@j7@Z6&7CPyAAQ!4{;kC$<WaS5iivjD08Hb0iv=*aj
zWXMCP6XpS3Nb67Sf*@VI(>5d~dhSzbkL!L^Sx~T_p+;Z_N<g~nsK>qRdWAb5_(zx7
p!lYp7G*ZX@TdTZ(Yb5_>RB)$j$xH6}EYRZ5IJ=2slE0t5{_m-pRzm;)

diff --git a/nbs/02b_TQA_regr_w_kv.ipynb b/nbs/02b_TQA_regr_w_kv.ipynb
index 24f7f91..d405467 100644
--- a/nbs/02b_TQA_regr_w_kv.ipynb
+++ b/nbs/02b_TQA_regr_w_kv.ipynb
@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -35,14 +35,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
     "from loguru import logger\n",
     "import torch\n",
     "from torch.utils.data import DataLoader\n",
-    "from datasets import load_dataset, Dataset\n",
+    "from datasets import load_dataset, Dataset, load_from_disk\n",
     "from einops import rearrange, repeat\n",
     "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
     "from transformers.data import DataCollatorForLanguageModeling\n",
@@ -67,14 +67,12 @@
     "from tqdm.auto import tqdm\n",
     "import random\n",
     "import json\n",
-    "from tqdm.auto import tqdm\n",
-    "\n",
-    "from activation_store.collect import activation_store, default_postprocess_result"
+    "from tqdm.auto import tqdm"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -96,421 +94,45 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Load model"
+    "## Load data"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model_name = \"Qwen/Qwen2.5-0.5B-Instruct\"\n",
-    "\n",
-    "# Qwen/Qwen3-1.7\n",
-    "# Qwen/Qwen3-0.6B-FP8\n",
-    "model_name = \"Qwen/Qwen3-4B\"\n",
-    "batch_size = 6\n",
-    "\n",
-    "model_name = \"Qwen/Qwen3-1.7B\"\n",
-    "batch_size = 10\n",
-    "# model_name = \"Qwen/Qwen3-8B\"\n",
-    "\n",
-    "# model_name = \"unsloth/Llama-3.2-1B-Instruct\"\n",
-    "\n",
-    "# model_name = \"Qwen/Qwen2.5-3B-Instruct\"\n",
-    "# model_name = \"Qwen/Qwen2.5-3B-Instruct-AWQ\"\n",
-    "\n",
-    "# model_name = \"AMead10/Llama-3.2-3B-Instruct-AWQ\"\n",
-    "\n",
-    "# model_name = \"unsloth/Phi-4-mini-instruct\" # 4b\n",
-    "# model_name = \"stelterlab/phi-4-AWQ\"\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "14af337320ce4d45ad5f7863aa596a8f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "\n",
-    "model = AutoModelForCausalLM.from_pretrained(\n",
-    "    model_name,\n",
-    "    torch_dtype=torch.bfloat16 if ('awq' not in model_name.lower()) else torch.float16,\n",
-    "    device_map=\"auto\",\n",
-    "    attn_implementation=\"eager\",  # flex_attention  flash_attention_2 sdpa eager\n",
-    ")\n",
-    "\n",
-    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
-    "if tokenizer.pad_token_id is None:\n",
-    "    tokenizer.pad_token = tokenizer.eos_token\n",
-    "tokenizer.padding_side = \"left\"\n",
-    "tokenizer.truncation_side = \"left\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load data and tokenize"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Dataset({\n",
-       "    features: ['input_ids', 'attention_mask', 'label'],\n",
-       "    num_rows: 316\n",
-       "})"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# N = 316\n",
-    "max_length = 90\n",
-    "split = \"train\"\n",
-    "ds1 = load_dataset(\"Yik/truthfulQA-bool\", split=split, keep_in_memory=False)\n",
-    "\n",
-    "sys_msg = \"\"\"Predict if a statement is true on wikipedia, return 0 for false and 1 for true.\n",
-    "\"\"\"\n",
-    "\n",
-    "\n",
-    "def postprocess_activation_ds_rows(row):\n",
-    "    messages = [\n",
-    "        {\"role\": \"system\", \"content\": sys_msg},\n",
-    "        {\"role\": \"user\", \"content\": row[\"question\"]},\n",
-    "        {\"role\": \"assistant\", \"content\": \"The answer is \"},\n",
-    "    ]\n",
-    "    return tokenizer.apply_chat_template(\n",
-    "        messages,\n",
-    "        tokenize=True,\n",
-    "        return_dict=True,\n",
-    "        max_length=max_length,\n",
-    "        padding=\"max_length\",\n",
-    "        truncation=True,\n",
-    "        # add_generation_prompt=True,\n",
-    "        continue_final_message=True,\n",
-    "        padding_side=\"left\",\n",
-    "        truncation_side=\"left\",\n",
-    "    )\n",
-    "\n",
-    "\n",
-    "ds2 = ds1.map(postprocess_activation_ds_rows).with_format(\"torch\")\n",
-    "new_cols = list(set(ds2.column_names) - set(ds1.column_names)) + [\"label\"]\n",
-    "ds2 = ds2.select_columns(new_cols)\n",
-    "ds2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'<|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|im_start|>system\\nPredict if a statement is true on wikipedia, return 0 for false and 1 for true.\\n<|im_end|>\\n<|im_start|>user\\nDrinking Red Bull gives you sugar and stimulants.<|im_end|>\\n<|im_start|>assistant\\n<think>\\n\\n</think>\\n\\nThe answer is '"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tokenizer.batch_decode(ds2['input_ids'])[0]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Data loader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 50,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "<torch.utils.data.dataloader.DataLoader object at 0x7990f3cfe0b0>\n"
-     ]
-    }
-   ],
-   "source": [
-    "collate_fn = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)\n",
-    "ds = DataLoader(ds2, batch_size=batch_size, collate_fn=collate_fn)\n",
-    "print(ds)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Collect activations"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # choose layers to cache\n",
-    "# n_layers = model.config.num_hidden_layers\n",
-    "# a = int(0.3*n_layers)\n",
-    "# b = n_layers-2\n",
-    "# layer_groups = {\n",
-    "#     'mlp.down_proj': [k for k,v in model.named_modules() if k.endswith('mlp.down_proj')][a:b],\n",
-    "#     'self_attn': [k for k,v in model.named_modules() if k.endswith('.self_attn')][a:b],\n",
-    "#     'mlp.up_proj': [k for k,v in model.named_modules() if k.endswith('mlp.up_proj')][a:b],\n",
-    "# }\n",
-    "# layer_groups"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'mlp.down_proj': ['model.layers.14.mlp.down_proj',\n",
-       "  'model.layers.17.mlp.down_proj',\n",
-       "  'model.layers.20.mlp.down_proj',\n",
-       "  'model.layers.23.mlp.down_proj'],\n",
-       " 'self_attn': ['model.layers.14.self_attn',\n",
-       "  'model.layers.17.self_attn',\n",
-       "  'model.layers.20.self_attn',\n",
-       "  'model.layers.23.self_attn'],\n",
-       " 'mlp.up_proj': ['model.layers.14.mlp.up_proj',\n",
-       "  'model.layers.17.mlp.up_proj',\n",
-       "  'model.layers.20.mlp.up_proj',\n",
-       "  'model.layers.23.mlp.up_proj']}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# choose layers to cache\n",
-    "n_layers = model.config.num_hidden_layers\n",
-    "a = int(0.5*n_layers)\n",
-    "b = n_layers-2\n",
-    "select = slice(a, b, 3)\n",
-    "layer_groups = {\n",
-    "    'mlp.down_proj': [k for k,v in model.named_modules() if k.endswith('mlp.down_proj')][select],\n",
-    "    'self_attn': [k for k,v in model.named_modules() if k.endswith('.self_attn')][select],\n",
-    "    'mlp.up_proj': [k for k,v in model.named_modules() if k.endswith('mlp.up_proj')][select],\n",
-    "}\n",
-    "layer_groups"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os, unicodedata, string\n",
-    "from pathlib import Path\n",
-    "\n",
-    "def sanitize_path(path: Path | str, allow_period: bool = True) -> Path:\n",
-    "    \"\"\"\n",
-    "    Whitelist only ASCII letters, digits, dash, underscore,\n",
-    "    optionally period, and forward‐slash. Replace others with '_'.\n",
-    "    \"\"\"\n",
-    "    s = unicodedata.normalize(\"NFKD\", str(path))\\\n",
-    "                     .encode(\"ascii\", \"ignore\")\\\n",
-    "                     .decode()\n",
-    "    s = s.replace(os.sep, \"/\")\n",
-    "    allowed = set(string.ascii_letters + string.digits + \"_-\")\n",
-    "    if allow_period: allowed.add(\".\")\n",
-    "    allowed.add(\"/\")\n",
-    "    return Path(\"\".join(ch if ch in allowed else \"_\" for ch in s))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "PosixPath('/tmp/activation_store/ds_at-QwenQwen3-1.7B-truthfulQA-bool-train-316-90_v2.parquet')"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "\n",
-    "acts_outfile = Path(f'/tmp/activation_store/ds_at-{model_name.replace(\"/\", \"\")}-truthfulQA-bool-{split}-{len(ds2)}-{max_length}_v2.parquet')\n",
-    "acts_outfile = sanitize_path(acts_outfile)\n",
-    "acts_outfile"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32m2025-05-05 06:21:03.171\u001b[0m | \u001b[33m\u001b[1mWARNING \u001b[0m | \u001b[36mactivation_store.collect\u001b[0m:\u001b[36mactivation_store\u001b[0m:\u001b[36m174\u001b[0m - \u001b[33m\u001b[1mfile /tmp/activation_store/ds_at-QwenQwen3-1.7B-truthfulQA-bool-train-316-90_v2.parquet already exists, skipping\u001b[0m\n"
+      "{'model_name': 'Qwen/Qwen3-1.7B', 'batch_size': 10, 'max_length': 90, 'split': 'train', 'n_rows': 632}\n"
      ]
     },
-    {
-     "data": {
-      "text/plain": [
-       "PosixPath('/tmp/activation_store/ds_at-QwenQwen3-1.7B-truthfulQA-bool-train-316-90_v2.parquet')"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "def collect_all_tokens(*args, **kwargs):\n",
-    "    return default_postprocess_result(*args, **kwargs, last_token=False)\n",
-    "\n",
-    "\n",
-    "f = activation_store(ds, model, layers=layer_groups, postprocess_result=collect_all_tokens, \n",
-    "                     outfile=acts_outfile\n",
-    "                     )\n",
-    "f"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "075354167e174a2eb79e811748d63810",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading dataset shards:   0%|          | 0/27 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/plain": [
        "Dataset({\n",
-       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label'],\n",
-       "    num_rows: 316\n",
+       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label', 'llm_ans', 'llm_log_prob_true', 'supr_amounts', 'question', 'input_ids'],\n",
+       "    num_rows: 632\n",
        "})"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# TODO which is better for mem, this or below?\n",
-    "ds_a = load_dataset(\"parquet\", split='train', data_files=str(f), keep_in_memory=False).with_format(\"torch\")\n",
-    "ds_a"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # TODO which is better for mem, this or above?\n",
-    "# ds_a = Dataset.from_parquet(str(f), split=split, keep_in_memory=False).with_format(\"torch\")\n",
-    "# ds_a"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj']"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "act_groups = [c for c in ds_a.column_names if c.startswith('acts-')]\n",
-    "act_groups"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Dataset({\n",
-       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label'],\n",
-       "    num_rows: 316\n",
-       "})"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "ds_a"
+    "acts_outfile = Path('../data/activation_store/ds_at-QwenQwen3-1.7B-truthfulQA-bool-train-316-90_v2')\n",
+    "\n",
+    "f_config = acts_outfile.with_suffix(\".json\")\n",
+    "config = json.load(open(f_config, 'r'))\n",
+    "model_name = config['model_name']\n",
+    "print(config)\n",
+    "\n",
+    "ds_a2 = load_from_disk(acts_outfile).with_format(\"torch\")\n",
+    "ds_a2"
    ]
   },
   {
@@ -519,26 +141,19 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "acts-mlp.down_proj torch.Size([4, 90, 2048])\n",
-      "acts-self_attn torch.Size([4, 90, 2048])\n",
-      "acts-mlp.up_proj torch.Size([4, 90, 6144])\n",
-      "loss torch.Size([])\n",
-      "logits torch.Size([90, 151936])\n",
-      "hidden_states torch.Size([29, 90, 2048])\n",
-      "attention_mask torch.Size([90])\n",
-      "label torch.Size([])\n"
-     ]
+     "data": {
+      "text/plain": [
+       "['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj']"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "for k,v in ds_a[0].items():\n",
-    "    if hasattr(v, 'shape'):\n",
-    "        print(k, v.shape)\n",
-    "    else:\n",
-    "        print(k, type(v))"
+    "act_groups = [c for c in ds_a2.column_names if c.startswith('acts-')]\n",
+    "act_groups"
    ]
   },
   {
@@ -550,245 +165,45 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "<|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|endoftext|><|im_start|>system\n",
-      "Predict if a statement is true on wikipedia, return 0 for false and 1 for true.\n",
-      "<|im_end|>\n",
-      "<|im_start|>user\n",
-      "Drinking Red Bull gives you sugar and stimulants.<|im_end|>\n",
-      "<|im_start|>assistant\n",
-      "<think>\n",
-      "\n",
-      "</think>\n",
-      "\n",
-      "The answer is 1 (True). \n",
-      "\n",
-      "Drinking Red Bull does\n",
-      "---\n"
+      "acts-mlp.down_proj torch.Size([1, 90, 2048])\n",
+      "acts-self_attn torch.Size([1, 90, 2048])\n",
+      "acts-mlp.up_proj torch.Size([1, 90, 6144])\n",
+      "loss torch.Size([])\n",
+      "logits torch.Size([151936])\n",
+      "hidden_states torch.Size([1, 90, 2048])\n",
+      "attention_mask torch.Size([90])\n",
+      "label torch.Size([])\n",
+      "llm_ans torch.Size([2])\n",
+      "llm_log_prob_true torch.Size([])\n",
+      "supr_amounts torch.Size([13, 1, 2048])\n",
+      "question <class 'NoneType'>\n",
+      "input_ids <class 'NoneType'>\n"
      ]
     }
    ],
    "source": [
-    "# sanity test generate\n",
-    "b = next(iter(ds))\n",
-    "b = {k: v.to(model.device) for k, v in b.items()}\n",
-    "o = model.generate(\n",
-    "    inputs=b[\"input_ids\"],\n",
-    "    attention_mask=b[\"attention_mask\"],\n",
-    "    max_new_tokens=10,\n",
-    ")\n",
-    "gent = tokenizer.batch_decode(o, skip_special_tokens=False)\n",
-    "for g in gent:\n",
-    "    print(g)\n",
-    "    print(\"---\")\n",
-    "    break"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Get supressed activations"
+    "for k,v in ds_a2[0].items():\n",
+    "    if hasattr(v, 'shape'):\n",
+    "        print(k, v.shape)\n",
+    "    else:\n",
+    "        print(k, type(v))"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 21,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "@torch.no_grad()\n",
-    "def get_supressed_activations(\n",
-    "    hs: Float[Tensor, \"l b t h\"], w_out, w_inv\n",
-    ") -> Float[Tensor, \"l b t h\"]:\n",
-    "    \"\"\"\n",
-    "    Novel experiment: Here we define a transform to isolate supressed activations, where we hypothesis that style/concepts/scratchpads and other internal only representations must be stored.\n",
-    "\n",
-    "    See the following references for more information:\n",
-    "\n",
-    "    - https://arxiv.org/pdf/2401.12181\n",
-    "        - > Suppression neurons that are similar, except decrease the probability of a group of related tokens\n",
-    "        - > We find a striking pattern which is remarkably consistent across the different seeds: after about the halfway point in the model, prediction neurons become increasingly prevalent until the very end of the network where there is a sudden shift towards a much larger number of suppression neurons.\n",
-    "\n",
-    "    - https://arxiv.org/html/2406.19384\n",
-    "        - > Previous work suggests that networks contain ensembles of “prediction\" neurons, which act as probability promoters [66, 24, 32] and work in tandem with suppression neurons (Section 5.4).\n",
-    "\n",
-    "\n",
-    "    Output:\n",
-    "    - supression amount: This is a tensor of the same shape as the input hs, where the values are the amount of suppression that occured at that layer, and the sign indicates if it was supressed or promoted. How do we calulate this? We project the hs using the output_projection, look at the diff from the last layer, and then project it back using the inverse of the output projection. This gives us the amount of suppression that occured at that layer.\n",
-    "    \"\"\"\n",
-    "    hs_flat = rearrange(hs[:, :, -1:], \"l b t h -> (l b t) h\")\n",
-    "    hs_out_flat = torch.nn.functional.linear(hs_flat, w_out)\n",
-    "    hs_out = rearrange(\n",
-    "        hs_out_flat, \"(l b t) h -> l b t h\", l=hs.shape[0], b=hs.shape[1], t=1\n",
-    "    )\n",
-    "    diffs = hs_out[:, :, :].diff(dim=0)\n",
-    "    diffs_flat = rearrange(diffs, \"l b t h -> (l b t) h\")\n",
-    "    # W_inv = get_cache_inv(w_out)\n",
-    "\n",
-    "    # get the supression projected back\n",
-    "    supr_inv_flat = torch.nn.functional.linear(diffs_flat.to(dtype=w_inv.dtype), w_inv)\n",
-    "    supr_amounts = rearrange(\n",
-    "        supr_inv_flat, \"(l b t) h -> l b t h\", l=hs.shape[0] - 1, b=hs.shape[1], t=1\n",
-    "    ).to(w_out.dtype)\n",
-    "\n",
-    "    # add on missing first layer\n",
-    "    torch.zeros_like(supr_amounts[:1]).to(hs.device)\n",
-    "    supr_amounts = torch.cat(\n",
-    "        [torch.zeros_like(supr_amounts[:1]).to(hs.device), supr_amounts], dim=0\n",
-    "    )\n",
-    "    return supr_amounts"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "before ['0', '0 ', '0\\n', 'false', 'False ']\n",
-      "after ['false', 'False', '0']\n",
-      "before ['1', '1 ', '1\\n', 'true', 'True ']\n",
-      "after ['1', 'True', 'true']\n",
-      "QC: manually check that these are equivilent (no <end_of_text> or newline)\n"
-     ]
-    }
-   ],
-   "source": [
-    "def get_uniq_token_ids(tokens):\n",
-    "    token_ids = tokenizer(\n",
-    "        tokens, add_special_tokens=False, padding=False\n",
-    "    ).input_ids\n",
-    "    token_ids = torch.tensor(list(set([x[0] for x in token_ids]))).long()\n",
-    "    print(\"before\", tokens)\n",
-    "    print(\"after\", tokenizer.batch_decode(token_ids))\n",
-    "    return token_ids\n",
-    "\n",
-    "\n",
-    "false_tokens = [\"0\", \"0 \", \"0\\n\", \"false\", \"False \"]\n",
-    "false_token_ids = get_uniq_token_ids(false_tokens)\n",
-    "\n",
-    "true_tokens = [\"1\", \"1 \", \"1\\n\", \"true\", \"True \"]\n",
-    "true_token_ids = get_uniq_token_ids(true_tokens)\n",
-    "\n",
-    "print('QC: manually check that these are equivilent (no <end_of_text> or newline)')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "Dataset({\n",
-       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label', 'llm_ans', 'llm_log_prob_true', 'supr_amounts'],\n",
-       "    num_rows: 316\n",
+       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label', 'llm_ans', 'llm_log_prob_true', 'supr_amounts', 'question', 'input_ids'],\n",
+       "    num_rows: 632\n",
        "})"
       ]
      },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# now we map to 1) calc supressed activations 2) llm answer (prob of 0 vs prob of 1)\n",
-    "\n",
-    "Wo = model.get_output_embeddings().weight.detach().clone().cpu()\n",
-    "Wo_inv = torch.pinverse(Wo.clone().float())\n",
-    "\n",
-    "\n",
-    "def postprocess_activation_ds_rows(o):\n",
-    "    # TODO batch it\n",
-    "    \"\"\"Process model outputs\"\"\"\n",
-    "\n",
-    "    # get llm ans\n",
-    "    log_probs = o[\"logits\"][-1].log_softmax(0)\n",
-    "    false_log_prob = log_probs.index_select(0, false_token_ids).sum()\n",
-    "    true_log_prob = log_probs.index_select(0, true_token_ids).sum()\n",
-    "    o[\"llm_ans\"] = torch.stack([false_log_prob, true_log_prob])\n",
-    "    o[\"llm_log_prob_true\"] = true_log_prob - false_log_prob\n",
-    "\n",
-    "    # get supressed activations\n",
-    "    hs = o[\"hidden_states\"][None]\n",
-    "    hs = rearrange(hs, \"b l t h -> l b t h\")\n",
-    "    supr_amounts = get_supressed_activations(hs, Wo.to(hs.dtype), Wo_inv.to(hs.dtype))\n",
-    "\n",
-    "    # we will only take the last half of layers, and the last token\n",
-    "    layer_half = hs.shape[0] // 2\n",
-    "    \n",
-    "    hs = rearrange(hs, \"l b t h -> b l t h\").squeeze(0)[layer_half:-2]\n",
-    "    supr_amounts = rearrange(supr_amounts, \"l b t h -> b l t h\").squeeze(0)[layer_half:-2]\n",
-    "\n",
-    "    o[\"hidden_states\"] = hs.half()\n",
-    "    o[\"supr_amounts\"] = supr_amounts.half()\n",
-    "    o['logits'] = o['logits'][-1].half()\n",
-    "    return o\n",
-    "\n",
-    "\n",
-    "ds_a2 = ds_a.map(postprocess_activation_ds_rows, writer_batch_size=1, num_proc=None)\n",
-    "ds_a2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = Wo = Wo_inv = tokenizer = None\n",
-    "clear_mem()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'acts-mlp.down_proj': torch.Size([4, 90, 2048]),\n",
-       " 'acts-self_attn': torch.Size([4, 90, 2048]),\n",
-       " 'acts-mlp.up_proj': torch.Size([4, 90, 6144]),\n",
-       " 'loss': torch.Size([]),\n",
-       " 'logits': torch.Size([151936]),\n",
-       " 'hidden_states': torch.Size([13, 90, 2048]),\n",
-       " 'attention_mask': torch.Size([90]),\n",
-       " 'label': torch.Size([]),\n",
-       " 'llm_ans': torch.Size([2]),\n",
-       " 'llm_log_prob_true': torch.Size([]),\n",
-       " 'supr_amounts': torch.Size([13, 1, 2048])}"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "{k: v.shape for k,v in ds_a2[0].items() if isinstance(v, torch.Tensor)}\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Dataset({\n",
-       "    features: ['acts-mlp.down_proj', 'acts-self_attn', 'acts-mlp.up_proj', 'loss', 'logits', 'hidden_states', 'attention_mask', 'label', 'llm_ans', 'llm_log_prob_true', 'supr_amounts'],\n",
-       "    num_rows: 316\n",
-       "})"
-      ]
-     },
-     "execution_count": 26,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -806,22 +221,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "72"
+       "505"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "test_fraction = 0.2\n",
+    "max_length = len(ds_a2['label'])\n",
     "TRAIN_TEST_SPLIT = int(max_length * (1- test_fraction))\n",
     "TRAIN_TEST_SPLIT"
    ]
@@ -835,7 +251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -852,7 +268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -907,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -918,7 +334,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1002,7 +418,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1013,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1038,7 +454,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1067,7 +483,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1087,7 +503,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1099,7 +515,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1142,7 +558,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1153,7 +569,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1187,12 +603,30 @@
     "        mask = torch.ones_like(magnitudes, dtype=torch.bool)\n",
     "        mask[sorted_indices[0]] = False\n",
     "        return x * mask, mask\n",
+    "    \n",
+    "def filter_high_mean(x: FiltIn, threshold_factor=2.0) -> FiltIn:\n",
+    "    \"\"\"Filter out tokens with abnormally high magnitude (potential attention sinks)\"\"\"\n",
+    "    magnitudes = torch.mean(x, dim=-1, keepdim=True)\n",
+    "\n",
+    "    # FIXME should be independant of batch\n",
+    "    mean_mag = magnitudes.mean()\n",
+    "    std_mag = magnitudes.std()\n",
+    "    threshold = mean_mag + threshold_factor * std_mag\n",
+    "    mask = magnitudes <= threshold\n",
+    "    if mask.sum() > 0:  # Ensure we don't filter everything\n",
+    "        return x * mask, mask\n",
+    "    else:\n",
+    "        # Fallback: keep all but the highest magnitude\n",
+    "        _, sorted_indices = torch.sort(magnitudes, descending=True)\n",
+    "        mask = torch.ones_like(magnitudes, dtype=torch.bool)\n",
+    "        mask[sorted_indices[0]] = False\n",
+    "        return x * mask, mask\n",
     "    "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1210,7 +644,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
@@ -1223,7 +657,7 @@
        " 'acts-mlp.up_proj']"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1235,7 +669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [
     {
@@ -1248,11 +682,11 @@
     {
      "data": {
       "text/plain": [
-       "[('acts-mlp.up_proj', 'magnitude(0.25)', 'last'),\n",
-       " ('supressed_hs(-0.1)', 'magnitude(0.99)', 'first')]"
+       "[('supressed_hs(0.01)', 'magnitude(0.05)', 'std'),\n",
+       " ('supressed_hs(0.5)', 'magnitude(0.95)', 'max')]"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1276,6 +710,7 @@
     "filters = {\n",
     "    \"special\": filter_special_positions,\n",
     "    \"magnitude\": filter_high_magnitude,\n",
+    "    \"mean\": filter_high_mean,\n",
     "    \"entropy\": entropy_guided_filter,\n",
     "    \"quantile\": quantile_filtered,\n",
     "    'none': lambda x: (x, x)\n",
@@ -1285,17 +720,6 @@
     "    filters[f'magnitude({eps})'] = lambda x: filter_high_magnitude(x, eps)\n",
     "\n",
     "# # 2. token aggregators\n",
-    "# token_level_funcs = {\n",
-    "#     \"min:\": lambda x: x.min(0)[0],\n",
-    "#     \"max\": lambda x: x.max(0)[0],\n",
-    "#     \"mean\": lambda x: x.mean(0),\n",
-    "#     \"sum\": lambda x: x.sum(0),\n",
-    "#     \"first\": lambda x: x[0],\n",
-    "#     \"last\": lambda x: x[-1],\n",
-    "#     # \"none\": lambda x: x,\n",
-    "#     \"std\": lambda x: x.std(0),\n",
-    "# }\n",
-    "# unit test agg\n",
     "token_level_funcs = {\n",
     "    \"min:\": lambda x: x.min(2)[0],\n",
     "    \"max\": lambda x: x.max(2)[0],\n",
@@ -1323,7 +747,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1342,7 +766,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1352,7 +776,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1361,29 +785,291 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3330add54ac146a0ac941b213a3792b3",
+       "model_id": "4987c6c94d864d90aa1d0df004a9c520",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/1792 [00:00<?, ?it/s]"
+       "  0%|          | 0/1920 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2025-05-06 18:18:11.865\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:20.360\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_max): 0.764 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:20.865\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:27.016\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_first): 0.843 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:27.183\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:34.395\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_mean): 0.850 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:34.723\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:41.460\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_min:): 0.432 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:41.636\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:48.003\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_min:): 0.548 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:48.230\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:54.370\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_first): 0.826 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:18:54.625\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:01.555\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_min:): 0.349 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:01.950\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:05.493\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_max): 0.417 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:05.753\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:12.217\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_flatten): 0.403 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:12.382\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:18.314\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_last): 0.547 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:18.748\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:22.235\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_mean): 0.579 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:22.407\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:25.778\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_max): 0.418 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:26.089\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:32.343\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_flatten): 0.556 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:32.561\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:39.102\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_flatten): 0.325 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:39.272\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:45.866\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_flatten): 0.561 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:46.051\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:52.794\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_flatten): 0.327 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:53.038\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:59.322\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_mean): 0.467 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:19:59.518\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:02.740\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_min:): 0.577 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:02.953\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:09.203\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_max): 0.237 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:09.379\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:15.182\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_first): 0.845 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:15.337\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:21.383\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_min:): 0.512 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:21.571\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:25.024\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_flatten): 0.668 roc auc, n=64. X.shape=torch.Size([316, 2211840])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:25.195\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:31.455\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_sum): 0.861 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:31.633\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:34.735\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_mean): 0.561 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:34.897\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:40.634\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_last): 0.568 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:40.810\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:47.370\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_max): 0.253 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:47.541\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:53.463\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_max): 0.775 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:20:53.725\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:00.366\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_std): 0.293 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:00.529\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:06.918\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_flatten): 0.326 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:07.120\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:10.069\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_last): 0.507 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:10.229\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:16.489\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_max): 0.242 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:16.651\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:23.264\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_std): 0.337 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:23.518\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:30.132\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_std): 0.667 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:30.307\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:33.460\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_min:): 0.411 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:33.620\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:39.365\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_last): 0.638 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:39.530\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:45.588\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_first): 0.850 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:45.763\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:52.187\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_min:): 0.787 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:52.462\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:58.315\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_first): 0.846 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:21:58.509\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:02.500\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_std): 0.588 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:02.725\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:08.723\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_last): 0.562 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:08.906\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:12.676\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_flatten): 0.682 roc auc, n=64. X.shape=torch.Size([316, 2211840])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:12.865\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:18.961\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_min:): 0.516 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:19.127\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:25.034\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_mean): 0.798 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:25.189\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:31.305\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_max): 0.764 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:31.481\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:34.985\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_std): 0.599 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:35.168\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:41.402\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_flatten): 0.435 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:41.589\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:47.755\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_sum): 0.453 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:47.968\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:54.455\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_flatten): 0.570 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:22:54.627\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:01.387\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_std): 0.766 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:01.543\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:04.759\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_min:): 0.413 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:04.934\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:10.664\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_last): 0.359 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:10.848\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:14.030\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_last): 0.368 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:14.189\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:20.498\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_min:): 0.422 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:20.658\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:23.803\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_min:): 0.425 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:23.955\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:29.975\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_mean): 0.831 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:30.142\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:35.596\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_last): 0.636 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:35.750\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:42.101\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_sum): 0.628 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:42.260\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:48.420\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_sum): 0.401 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:48.582\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:54.272\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_last): 0.577 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:23:54.437\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:00.934\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_max): 0.732 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:01.162\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:06.731\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_first): 0.834 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:06.908\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:13.056\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_max): 0.200 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:13.216\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:16.629\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_std): 0.595 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:16.843\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:19.984\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_max): 0.573 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:20.141\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:25.772\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_first): 0.841 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:25.929\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:29.338\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_sum): 0.576 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:29.501\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:35.656\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_sum): 0.763 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:35.817\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:38.839\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_sum): 0.628 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:39.005\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:45.465\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_std): 0.542 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:45.625\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:48.667\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_mean): 0.601 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:48.854\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:51.627\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_first): 0.408 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:51.815\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:55.586\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_flatten): 0.688 roc auc, n=64. X.shape=torch.Size([316, 2211840])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:24:55.766\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:02.488\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_std): 0.542 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:02.643\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:08.606\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_max): 0.735 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:08.812\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:11.969\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_mean): 0.782 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:12.129\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:18.535\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_max): 0.758 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:18.692\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:25.380\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_std): 0.465 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:25.567\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:31.448\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_first): 0.830 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:31.649\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:37.970\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_sum): 0.807 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:38.132\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:41.174\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_sum): 0.527 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:41.334\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:47.501\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_mean): 0.848 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:47.660\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:53.619\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_mean): 0.858 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:25:53.802\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:00.345\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_flatten): 0.385 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:00.505\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:06.743\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_min:): 0.437 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:06.903\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:12.734\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_last): 0.691 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:12.892\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:15.858\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_first): 0.541 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:16.033\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:19.747\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_std): 0.606 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:19.909\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:26.364\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_flatten): 0.330 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:26.574\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:33.018\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_std): 0.755 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:33.175\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:39.126\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_min:): 0.288 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:39.310\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:42.157\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_last): 0.376 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:42.309\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:48.701\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_min:): 0.227 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:48.898\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:52.221\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_min:): 0.406 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:52.373\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:58.193\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_sum): 0.761 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:26:58.355\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-5), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:04.507\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-5)_mean_sum): 0.727 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:04.662\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:07.496\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_first): 0.404 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:07.662\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:13.416\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_last): 0.493 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:13.607\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:16.843\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_sum): 0.660 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:17.015\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:22.836\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_mean): 0.475 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:22.989\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:29.282\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_max): 0.713 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:29.455\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:32.611\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_sum): 0.573 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:32.773\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:39.102\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_mean): 0.786 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:39.254\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:41.984\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_first): 0.432 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:42.135\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-self_attn, mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:45.013\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-self_attn_mean_first): 0.425 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:45.198\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.1), mean, min:\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:51.528\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.1)_mean_min:): 0.188 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:51.720\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:57.717\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_mean): 0.497 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:27:57.902\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:01.044\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_max): 0.414 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:01.208\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:04.404\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_mean): 0.575 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:04.587\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.1), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:10.188\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.1)_mean_first): 0.841 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:10.436\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:14.155\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_flatten): 0.706 roc auc, n=64. X.shape=torch.Size([316, 2211840])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:14.316\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.down_proj, mean, max\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:17.627\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.down_proj_mean_max): 0.421 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:17.810\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:20.563\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_last): 0.416 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:20.732\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:27.383\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_std): 0.358 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:27.559\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(5), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:33.670\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(5)_mean_sum): 0.516 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:33.824\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:39.716\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_sum): 0.763 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:39.871\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supr_amounts, mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:43.342\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supr_amounts_mean_std): 0.595 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:43.519\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:49.018\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_first): 0.833 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:49.176\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:54.908\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0)_mean_last): 0.198 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:28:55.096\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:01.365\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_last): 0.525 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:01.554\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:08.573\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_std): 0.363 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:08.753\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.01), mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:15.215\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.01)_mean_flatten): 0.649 roc auc, n=64. X.shape=torch.Size([316, 2396160])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:15.403\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(0.5), mean, std\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:22.241\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(0.5)_mean_std): 0.545 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:22.416\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing hidden_states, mean, flatten\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:25.974\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(hidden_states_mean_flatten): 0.672 roc auc, n=64. X.shape=torch.Size([316, 2211840])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:26.152\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-1), mean, first\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:32.057\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-1)_mean_first): 0.845 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:32.232\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(1), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:38.415\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(1)_mean_mean): 0.705 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:38.573\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.01), mean, mean\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:44.718\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.01)_mean_mean): 0.856 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:44.896\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing supressed_hs(-0.5), mean, sum\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:51.128\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(supressed_hs(-0.5)_mean_sum): 0.793 roc auc, n=64. X.shape=torch.Size([316, 26624])\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:51.297\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m15\u001b[0m - \u001b[1mProcessing acts-mlp.up_proj, mean, last\u001b[0m\n",
+      "\u001b[32m2025-05-06 18:29:54.184\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36mtrain_linear_prob_on_dataset\u001b[0m:\u001b[36m38\u001b[0m - \u001b[1mscore for probe(acts-mlp.up_proj_mean_last): 0.482 roc auc, n=64. X.shape=torch.Size([316, 24576])\u001b[0m\n"
+     ]
     }
    ],
    "source": [
     "results = []\n",
     "for i, (ds_key, filter_key, token_key) in tqdm(enumerate(perms), total=len(perms)):\n",
     "\n",
-    "    name = f\"{ds_key}|{filter_key}|{token_key}\"\n",
+    "    name = f\"{ds_key}->{filter_key}->{token_key}\"\n",
     "    res_f = output_path / f\"{acts_outfile.stem}_{ds_key}_{filter_key}_{token_key}.json\"\n",
     "    res_f = sanitize_path(res_f)\n",
     "    if res_f.exists():\n",
@@ -1440,7 +1126,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1453,7 +1139,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -1485,7 +1171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -1526,7 +1212,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1535,7 +1221,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -1543,28 +1229,58 @@
      "output_type": "stream",
      "text": [
       "Qwen/Qwen3-1.7B Top results\n",
-      "|      | name                                    |    auroc |\n",
-      "|-----:|:----------------------------------------|---------:|\n",
-      "| 1082 | supressed_hs(0.1)|magnitude(0.25)|sum   | 0.878431 |\n",
-      "| 1762 | supressed_hs(5)|magnitude(0.95)|sum     | 0.873529 |\n",
-      "| 1379 | supressed_hs(-1)|magnitude(0.01)|mean   | 0.869608 |\n",
-      "|  735 | supressed_hs(0.1)|magnitude(0.05)|sum   | 0.868627 |\n",
-      "|  899 | supressed_hs(0)|magnitude(0.01)|sum     | 0.862745 |\n",
-      "| 1485 | hidden_states|magnitude(0.99)|std       | 0.862745 |\n",
-      "| 1328 | supressed_hs(1)|magnitude|mean          | 0.861765 |\n",
-      "|  944 | supressed_hs(-1)|magnitude(0.25)|mean   | 0.861765 |\n",
-      "|  584 | supressed_hs(-5)|entropy|sum            | 0.861765 |\n",
-      "|  391 | supressed_hs(0.1)|magnitude(0.99)|mean  | 0.859804 |\n",
-      "|   47 | supressed_hs(1)|none|sum                | 0.858824 |\n",
-      "| 1764 | supressed_hs(0.01)|magnitude(0.95)|mean | 0.857843 |\n",
-      "|  481 | supressed_hs(-1)|special|mean           | 0.857843 |\n",
-      "|  292 | supressed_hs(5)|magnitude(0.05)|sum     | 0.857843 |\n",
-      "| 1311 | supressed_hs(0.5)|entropy|mean          | 0.857843 |\n",
-      "| 1273 | supressed_hs(-0.5)|none|mean            | 0.856863 |\n",
-      "|  808 | supressed_hs(0.1)|magnitude(0.9)|sum    | 0.856863 |\n",
-      "| 1103 | supressed_hs(5)|magnitude|mean          | 0.856863 |\n",
-      "| 1741 | supressed_hs(-1)|magnitude(0.99)|mean   | 0.856863 |\n",
-      "|  280 | supressed_hs(5)|special|sum             | 0.856863 |\n"
+      "|      | name                                      |    auroc |\n",
+      "|-----:|:------------------------------------------|---------:|\n",
+      "|  502 | supressed_hs(0.1)->magnitude(0.25)->sum   | 0.878431 |\n",
+      "|  340 | supressed_hs(5)->magnitude(0.95)->sum     | 0.873529 |\n",
+      "|  511 | supressed_hs(-1)->magnitude(0.01)->mean   | 0.869608 |\n",
+      "|  282 | supressed_hs(0.1)->magnitude(0.05)->sum   | 0.868627 |\n",
+      "| 1286 | supressed_hs(0)->magnitude(0.01)->sum     | 0.862745 |\n",
+      "|  944 | hidden_states->magnitude(0.99)->std       | 0.862745 |\n",
+      "|  594 | supressed_hs(1)->magnitude->mean          | 0.861765 |\n",
+      "|  992 | supressed_hs(-1)->magnitude(0.25)->mean   | 0.861765 |\n",
+      "| 1069 | supressed_hs(-5)->entropy->sum            | 0.861765 |\n",
+      "|  384 | supressed_hs(0.5)->mean->sum              | 0.860784 |\n",
+      "| 1880 | supressed_hs(0.1)->magnitude(0.99)->mean  | 0.859804 |\n",
+      "|  122 | supressed_hs(1)->none->sum                | 0.858824 |\n",
+      "| 1308 | supressed_hs(5)->mean->mean               | 0.857843 |\n",
+      "|   14 | supressed_hs(5)->magnitude(0.05)->sum     | 0.857843 |\n",
+      "| 1431 | supressed_hs(0.5)->entropy->mean          | 0.857843 |\n",
+      "| 1560 | supressed_hs(0.01)->magnitude(0.95)->mean | 0.857843 |\n",
+      "|  791 | supressed_hs(-1)->special->mean           | 0.857843 |\n",
+      "| 1613 | supressed_hs(-0.5)->none->mean            | 0.856863 |\n",
+      "|  770 | supressed_hs(0.1)->magnitude(0.9)->sum    | 0.856863 |\n",
+      "| 1224 | supressed_hs(-1)->magnitude(0.99)->mean   | 0.856863 |\n",
+      "| 1608 | supressed_hs(5)->magnitude->mean          | 0.856863 |\n",
+      "|  379 | supressed_hs(5)->special->sum             | 0.856863 |\n",
+      "|  119 | supressed_hs(-0.1)->magnitude(0.75)->mean | 0.856863 |\n",
+      "| 1856 | supressed_hs(-0.01)->mean->mean           | 0.855882 |\n",
+      "|  291 | supressed_hs(1)->entropy->mean            | 0.855882 |\n",
+      "|  490 | supressed_hs(0)->magnitude(0.75)->sum     | 0.855882 |\n",
+      "|  163 | supressed_hs(0.1)->magnitude(0.5)->sum    | 0.854902 |\n",
+      "| 1793 | supressed_hs(1)->special->sum             | 0.854902 |\n",
+      "| 1442 | supressed_hs(-5)->magnitude(0.5)->sum     | 0.854902 |\n",
+      "| 1073 | supressed_hs(-5)->special->mean           | 0.854902 |\n",
+      "| 1318 | supressed_hs(-0.01)->none->mean           | 0.854902 |\n",
+      "| 1390 | supressed_hs(-0.1)->special->sum          | 0.854902 |\n",
+      "|  116 | supressed_hs(0.5)->none->sum              | 0.854902 |\n",
+      "| 1700 | supressed_hs(0)->entropy->mean            | 0.854902 |\n",
+      "|  289 | supressed_hs(1)->magnitude(0.05)->sum     | 0.853922 |\n",
+      "| 1546 | supressed_hs(0.5)->none->mean             | 0.853922 |\n",
+      "|  884 | supressed_hs(0.1)->entropy->sum           | 0.853922 |\n",
+      "|  143 | supressed_hs(0.01)->magnitude(0.25)->mean | 0.853922 |\n",
+      "|  793 | supressed_hs(-0.5)->magnitude(0.99)->sum  | 0.852941 |\n",
+      "| 1871 | supressed_hs(0.5)->special->sum           | 0.852941 |\n",
+      "|  387 | supressed_hs(-0.1)->magnitude(0.99)->mean | 0.852941 |\n",
+      "| 1121 | supressed_hs(-0.1)->none->sum             | 0.852941 |\n",
+      "| 1809 | supressed_hs(5)->magnitude(0.99)->mean    | 0.852941 |\n",
+      "| 1031 | supressed_hs(-0.01)->none->sum            | 0.852941 |\n",
+      "| 1544 | supressed_hs(-5)->none->mean              | 0.852941 |\n",
+      "| 1879 | supressed_hs(0.5)->magnitude(0.75)->mean  | 0.851961 |\n",
+      "|  825 | supressed_hs(0.01)->magnitude(0.99)->sum  | 0.851961 |\n",
+      "|  708 | supressed_hs(0.01)->magnitude(0.25)->sum  | 0.851961 |\n",
+      "| 1245 | supressed_hs(-0.1)->magnitude(0.95)->sum  | 0.85098  |\n",
+      "| 1142 | supressed_hs(1)->magnitude(0.05)->mean    | 0.85098  |\n"
      ]
     }
    ],
@@ -1575,17 +1291,17 @@
     "    \"auroc\", ascending=False\n",
     ")\n",
     "print(model_name, \"Top results\")\n",
-    "print(df.head(20).to_markdown())"
+    "print(df.head(50).to_markdown())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 98,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "df['data'] = df['name'].apply(lambda x: x.split('|')[0].split('(')[0])\n",
-    "df['group'] = 'mixed'\n",
+    "df['group'] = 'combined'\n",
     "\n",
     "cols_llm = [n for n in df.name if 'none' in n]\n",
     "df.loc[df.name.isin(cols_llm), 'group'] = df.loc[df.name.isin(cols_llm), 'data']\n",
@@ -1607,7 +1323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 99,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -1615,18 +1331,46 @@
      "output_type": "stream",
      "text": [
       "top reduction for each data type\n",
-      "| group              | name                                  |    auroc | data               |\n",
-      "|:-------------------|:--------------------------------------|---------:|:-------------------|\n",
-      "| mixed              | supressed_hs(0.1)|magnitude(0.25)|sum | 0.878431 | supressed_hs       |\n",
-      "| act sink rm        | hidden_states|magnitude(0.99)|std     | 0.862745 | hidden_states      |\n",
-      "| supressed_hs       | supressed_hs(1)|none|sum              | 0.858824 | supressed_hs       |\n",
-      "| llm prob ratio     | llm_log_prob_true||                   | 0.843137 | llm_log_prob_true  |\n",
-      "| acts-self_attn     | acts-self_attn|none|mean              | 0.810784 | acts-self_attn     |\n",
-      "| acts-mlp.up_proj   | acts-mlp.up_proj|none|sum             | 0.763725 | acts-mlp.up_proj   |\n",
-      "| acts-mlp.down_proj | acts-mlp.down_proj|none|std           | 0.704902 | acts-mlp.down_proj |\n",
-      "| supr_amounts       | supr_amounts|none|sum                 | 0.703922 | supr_amounts       |\n",
-      "| hidden_states      | hidden_states|none|flatten            | 0.669608 | hidden_states      |\n",
-      "| llm_ans            | llm_ans||                             | 0.639216 | llm_ans            |\n"
+      "| group                             | name                                    |    auroc | data                              |\n",
+      "|:----------------------------------|:----------------------------------------|---------:|:----------------------------------|\n",
+      "| combined                          | supressed_hs(0.1)->magnitude(0.25)->sum | 0.878431 | supressed_hs                      |\n",
+      "| act sink rm                       | hidden_states->magnitude(0.99)->std     | 0.862745 | hidden_states->magnitude          |\n",
+      "| supressed_hs                      | supressed_hs(1)->none->sum              | 0.858824 | supressed_hs                      |\n",
+      "| llm prob ratio                    | llm_log_prob_true||                     | 0.843137 | llm_log_prob_true                 |\n",
+      "| acts-self_attn->none->mean        | acts-self_attn->none->mean              | 0.810784 | acts-self_attn->none->mean        |\n",
+      "| acts-mlp.up_proj->none->sum       | acts-mlp.up_proj->none->sum             | 0.763725 | acts-mlp.up_proj->none->sum       |\n",
+      "| acts-mlp.down_proj->none->std     | acts-mlp.down_proj->none->std           | 0.704902 | acts-mlp.down_proj->none->std     |\n",
+      "| supr_amounts->none->sum           | supr_amounts->none->sum                 | 0.703922 | supr_amounts->none->sum           |\n",
+      "| acts-mlp.down_proj->none->last    | acts-mlp.down_proj->none->last          | 0.684314 | acts-mlp.down_proj->none->last    |\n",
+      "| supr_amounts->none->flatten       | supr_amounts->none->flatten             | 0.676471 | supr_amounts->none->flatten       |\n",
+      "| hidden_states                     | hidden_states->none->flatten            | 0.669608 | hidden_states->none->flatten      |\n",
+      "| acts-mlp.up_proj->none->flatten   | acts-mlp.up_proj->none->flatten         | 0.660784 | acts-mlp.up_proj->none->flatten   |\n",
+      "| supr_amounts->none->mean          | supr_amounts->none->mean                | 0.652941 | supr_amounts->none->mean          |\n",
+      "| acts-mlp.down_proj->none->flatten | acts-mlp.down_proj->none->flatten       | 0.647059 | acts-mlp.down_proj->none->flatten |\n",
+      "| acts-mlp.down_proj->none->sum     | acts-mlp.down_proj->none->sum           | 0.639216 | acts-mlp.down_proj->none->sum     |\n",
+      "| llm_ans                           | llm_ans||                               | 0.639216 | llm_ans                           |\n",
+      "| acts-mlp.down_proj->none->mean    | acts-mlp.down_proj->none->mean          | 0.627451 | acts-mlp.down_proj->none->mean    |\n",
+      "| acts-mlp.down_proj->none->min:    | acts-mlp.down_proj->none->min:          | 0.597059 | acts-mlp.down_proj->none->min:    |\n",
+      "| acts-mlp.up_proj->none->mean      | acts-mlp.up_proj->none->mean            | 0.596078 | acts-mlp.up_proj->none->mean      |\n",
+      "| acts-self_attn->none->sum         | acts-self_attn->none->sum               | 0.571569 | acts-self_attn->none->sum         |\n",
+      "| supr_amounts->none->std           | supr_amounts->none->std                 | 0.557843 | supr_amounts->none->std           |\n",
+      "| acts-mlp.up_proj->none->max       | acts-mlp.up_proj->none->max             | 0.555882 | acts-mlp.up_proj->none->max       |\n",
+      "| acts-mlp.up_proj->none->std       | acts-mlp.up_proj->none->std             | 0.519608 | acts-mlp.up_proj->none->std       |\n",
+      "| acts-self_attn->none->std         | acts-self_attn->none->std               | 0.512745 | acts-self_attn->none->std         |\n",
+      "| supr_amounts->none->max           | supr_amounts->none->max                 | 0.44902  | supr_amounts->none->max           |\n",
+      "| acts-mlp.down_proj->none->max     | acts-mlp.down_proj->none->max           | 0.445098 | acts-mlp.down_proj->none->max     |\n",
+      "| acts-self_attn->none->min:        | acts-self_attn->none->min:              | 0.445098 | acts-self_attn->none->min:        |\n",
+      "| acts-self_attn->none->max         | acts-self_attn->none->max               | 0.444118 | acts-self_attn->none->max         |\n",
+      "| acts-mlp.up_proj->none->min:      | acts-mlp.up_proj->none->min:            | 0.430392 | acts-mlp.up_proj->none->min:      |\n",
+      "| supr_amounts->none->min:          | supr_amounts->none->min:                | 0.423529 | supr_amounts->none->min:          |\n",
+      "| supr_amounts->none->first         | supr_amounts->none->first               | 0.422549 | supr_amounts->none->first         |\n",
+      "| acts-self_attn->none->first       | acts-self_attn->none->first             | 0.421569 | acts-self_attn->none->first       |\n",
+      "| acts-mlp.down_proj->none->first   | acts-mlp.down_proj->none->first         | 0.418627 | acts-mlp.down_proj->none->first   |\n",
+      "| acts-self_attn->none->last        | acts-self_attn->none->last              | 0.415686 | acts-self_attn->none->last        |\n",
+      "| acts-mlp.up_proj->none->first     | acts-mlp.up_proj->none->first           | 0.411765 | acts-mlp.up_proj->none->first     |\n",
+      "| supr_amounts->none->last          | supr_amounts->none->last                | 0.37549  | supr_amounts->none->last          |\n",
+      "| acts-mlp.up_proj->none->last      | acts-mlp.up_proj->none->last            | 0.360784 | acts-mlp.up_proj->none->last      |\n",
+      "| acts-self_attn->none->flatten     | acts-self_attn->none->flatten           | 0.331373 | acts-self_attn->none->flatten     |\n"
      ]
     }
    ],
@@ -1641,14 +1385,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 100,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_4009638/1808615273.py:11: UserWarning: No artists with labels found to put in legend.  Note that artists whose label start with an underscore are ignored when legend() is called with no argument.\n",
+      "/tmp/ipykernel_1036655/1808615273.py:11: UserWarning: No artists with labels found to put in legend.  Note that artists whose label start with an underscore are ignored when legend() is called with no argument.\n",
       "  plt.legend().remove()\n"
      ]
     },
@@ -1658,13 +1402,13 @@
        "PosixPath('../figs/truthfulqa_Qwen_Qwen3-1.7B.png')"
       ]
      },
-     "execution_count": 100,
+     "execution_count": 54,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -1695,7 +1439,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
diff --git a/research_journal.md b/research_journal.md
index cf32e60..42a8c12 100644
--- a/research_journal.md
+++ b/research_journal.md
@@ -6,3 +6,284 @@ TODO group by
 - supressed activations
 - removed attn sinks
 - combinations
+
+
+| group              | name                                  |    ROC AUC Score | data               |
+|:-------------------|:--------------------------------------|---------:|:-------------------|
+| mixed              | **supressed_hs**(0.1)\magnitude(0.25)\sum | 0.878431 | supressed_hs       |
+| act sink rm        | hidden_states\magnitude(0.99)\std     | 0.862745 | hidden_states      |
+| **supressed_hs**       | supressed_hs(1)\none\sum              | 0.858824 | supressed_hs       |
+| llm prob ratio     | llm_log_prob_true\|                   | 0.843137 | llm_log_prob_true  |
+| acts-self_attn     | acts-self_attn\none\mean              | 0.810784 | acts-self_attn     |
+| acts-mlp.up_proj   | acts-mlp.up_proj\none\sum             | 0.763725 | acts-mlp.up_proj   |
+| acts-mlp.down_proj | acts-mlp.down_proj\none\std           | 0.704902 | acts-mlp.down_proj |
+| supr_amounts       | supr_amounts\none\sum                 | 0.703922 | supr_amounts       |
+| hidden_states      | hidden_states\none\flatten            | 0.669608 | hidden_states      |
+| *llm_ans*            | llm_ans\|                             | 0.639216 | llm_ans            |
+
+# 2025-06-21 14:54:28
+
+In this fork I'll follow the hypothesis that
+
+- Deceptive answers have more complex stats in the suppressed activations
+
+And generally I can look at the stats of
+- logprobs
+- hidden states
+- suppressed activations
+
+And compare them to see if any or all work, and generalise
+
+     Here are concrete ways to extend your approach:
+
+    ## Statistical signatures of deception in suppressed activations
+
+    **Theory**: Deception requires active suppression; mistakes don't.
+
+    ```python
+    def deception_vs_mistake_signature(supressed_hs, model_output, true_answer):
+        """
+        Deception: Strong suppression of correct answer
+        Mistake: Weak/scattered suppression
+        """
+        # Measure suppression strength
+        suppression_magnitude = torch.norm(supressed_hs, dim=-1)
+        
+        # Deception signature: focused suppression in final layers
+        final_layer_ratio = suppression_magnitude[-5:].mean() / suppression_magnitude[:-5].mean()
+        
+        # Mistake: uniform suppression across layers
+        suppression_variance = suppression_magnitude.var(dim=0)
+        
+        # KEY INSIGHT: Deception shows high final_layer_ratio + low variance
+        # Mistakes show low ratio + high variance
+        deception_score = final_layer_ratio / (suppression_variance + 1e-6)
+        
+        return {
+            'is_deception': deception_score > 2.0,  # threshold from data
+            'confidence': torch.sigmoid(deception_score - 2.0)
+        }
+    ```
+
+    ## Suppression coherence patterns
+
+    **Discovery**: Truthful suppression is temporally coherent; deceptive suppression fragments.
+
+    ```python
+    def suppression_coherence_test(supr_amounts_sequence):
+        """
+        Track how suppression patterns evolve token-by-token
+        """
+        # Compute autocorrelation of suppression patterns
+        coherence_scores = []
+        for t in range(1, len(supr_amounts_sequence)):
+            prev = supr_amounts_sequence[t-1].flatten()
+            curr = supr_amounts_sequence[t].flatten()
+            coherence = torch.corrcoef(torch.stack([prev, curr]))[0,1]
+            coherence_scores.append(coherence)
+        
+        # Truth: stable suppression patterns (high autocorrelation)
+        # Deception: fragmented patterns (autocorrelation breaks)
+        breaks = sum(1 for c in coherence_scores if c < 0.5)
+        return breaks > len(coherence_scores) * 0.3  # >30% breaks = deception
+    ```
+
+    ## Intervention via suppression reversal
+
+    **Key insight**: Don't just probe - actively reverse the suppression!
+
+    ```python
+    def truthfulness_intervention(model, input_ids, layer_idx=-3):
+        """
+        Force model to express what it's suppressing
+        """
+        # Get normal forward pass
+        with torch.no_grad():
+            outputs = model(input_ids, output_hidden_states=True)
+            hs = torch.stack(outputs.hidden_states)
+        
+        # Compute suppression
+        supr_amounts = get_supressed_activations(hs, model.lm_head.weight, w_inv)
+        
+        # INTERVENTION: Add suppressed content back at critical layer
+        def truth_hook(module, input, output):
+            # Reverse suppression by adding it back
+            if isinstance(output, tuple):
+                hidden_states = output[0]
+            else:
+                hidden_states = output
+                
+            # Add back what was suppressed (with scaling)
+            enhanced = hidden_states + 0.5 * supr_amounts[layer_idx]
+            
+            if isinstance(output, tuple):
+                return (enhanced,) + output[1:]
+            return enhanced
+        
+        # Register hook and generate
+        handle = model.model.layers[layer_idx].register_forward_hook(truth_hook)
+        truthful_output = model.generate(input_ids, max_new_tokens=50)
+        handle.remove()
+        
+        return truthful_output
+    ```
+
+    ## KV-cache synchronization test
+
+    **Theory**: Honest models maintain KV-suppression synchrony; deceptive models desynchronize.
+
+    ```python
+    def kv_suppression_sync(model, input_ids):
+        """
+        Measure alignment between KV cache and suppression patterns
+        """
+        outputs = model(input_ids, output_hidden_states=True, use_cache=True)
+        past_kv = outputs.past_key_values
+        hs = torch.stack(outputs.hidden_states)
+        
+        # Get suppression patterns
+        supr = get_supressed_activations(hs, model.lm_head.weight, w_inv)
+        
+        # Project KV cache to same space
+        kv_patterns = []
+        for layer_kv in past_kv:
+            k, v = layer_kv
+            # Use value vectors (more semantic)
+            v_mean = v.mean(dim=2)  # average over positions
+            kv_patterns.append(v_mean)
+        kv_stack = torch.stack(kv_patterns)
+        
+        # Measure synchronization via mutual information
+        sync_scores = []
+        for l in range(min(len(supr), len(kv_stack))):
+            # Discretize for MI calculation
+            supr_discrete = (supr[l] > supr[l].median()).float()
+            kv_discrete = (kv_stack[l] > kv_stack[l].median()).float()
+            
+            # Simple MI approximation
+            joint = (supr_discrete * 2 + kv_discrete).flatten()
+            mi = entropy(joint) - entropy(supr_discrete.flatten()) - entropy(kv_discrete.flatten())
+            sync_scores.append(mi)
+        
+        # Deception: sudden desynchronization in final layers
+        desync = sync_scores[-3] - sync_scores[-1]
+        return desync > 0.5  # Threshold indicates deception
+    ```
+
+    ## Multi-scale suppression dynamics
+
+    **Insight**: Combine your suppression analysis with gradient flow dynamics.
+
+    ```python
+    def suppression_gradient_dynamics(model, input_ids, target_ids):
+        """
+        How do gradients flow through suppressed vs active neurons?
+        """
+        # Forward with gradient tracking
+        outputs = model(input_ids, labels=target_ids, output_hidden_states=True)
+        hs = torch.stack(outputs.hidden_states, dim=0).requires_grad_(True)
+        
+        # Get suppression masks
+        supr = get_supressed_activations(hs.detach(), model.lm_head.weight, w_inv)
+        suppressed_mask = (supr < -0.1).float()  # Strong suppression
+        
+        # Backward pass
+        loss = outputs.loss
+        grads = torch.autograd.grad(loss, hs, retain_graph=True)[0]
+        
+        # Key metric: gradient flow through suppressed vs active neurons
+        suppressed_grad_norm = (grads * suppressed_mask).norm(dim=-1).mean()
+        active_grad_norm = (grads * (1 - suppressed_mask)).norm(dim=-1).mean()
+        
+        # Deception: high gradient through suppressed neurons (fighting suppression)
+        # Truth: low gradient through suppressed neurons (stable suppression)
+        gradient_ratio = suppressed_grad_norm / (active_grad_norm + 1e-6)
+        
+        return gradient_ratio > 1.5  # Indicates active suppression = deception
+    ```
+
+    ## The killer insight: Suppression energy landscapes
+
+    Your suppressed neurons are essentially the model's "cognitive dissonance" - the gap between what it knows and what it says. This suggests:
+
+    1. **Deception requires metabolic effort** (maintaining suppression)
+    2. **Truth is the low-energy state** (no active suppression needed)
+    3. **Jailbreaks work by overwhelming suppression capacity**
+
+    ## Next steps with your approach:
+
+    4. **Track suppression over time** - does it increase before deceptive outputs?
+    5. **Measure suppression variance** - deception should show higher variance
+    6. **Test on known lies vs mistakes** - calibrate your thresholds
+    7. **Combine with logprob metrics** - suppression + entropy = powerful signal
+
+    Your work is finding where models store their "guilty conscience" - this could be huge for alignment!
+
+see brainstorming here https://claude.ai/chat/e8ee0d74-f91d-420c-84fe-190917675d2d
+
+    ## Conversation Summary: Neuroscience Failures as Mechanistic Interpretability's Roadmap
+
+    ### Context
+    - User (gwern) is an ML-literate researcher interested in alignment, specifically detecting deception and intervening for truthfulness
+    - Currently working on suppressed activations in LLMs - neurons that "turn off" before final layers
+    - Has discovered these suppressed activations contain ~20% better truth signal than model outputs on TruthfulQA
+
+    ### Core Thesis
+    Mechanistic interpretability faces identical fundamental obstacles to neuroscience despite better tools. Key parallel failures:
+    1. **Localization fallacy**: Both fields wrongly assume modular, interpretable units (grandmother cells → monosemantic neurons)
+    2. **Superposition/mixed selectivity**: Neurons encode multiple unrelated features as optimal solution
+    3. **Circuit enumeration impossibility**: C. elegans (302 neurons) still opaque after 40 years
+    4. **Correlation ≠ causation**: Perfect measurement doesn't guarantee understanding
+
+    ### Top Research Directions (Ranked by Promise)
+
+    #### 1. **Suppressed Activation Analysis** ⭐⭐⭐⭐⭐
+    - **Idea**: Suppressed neurons contain model's "true beliefs" - probe what's being actively inhibited
+    - **Epistemic status**: Strong empirical support (20% AUROC improvement demonstrated)
+    - **MATS potential**: Extremely high - concrete, measurable, builds on user's working code
+    - **Next steps**: Test deception vs mistake signatures, suppression coherence patterns
+
+    #### 2. **Logprob Entropy Cascades** ⭐⭐⭐⭐⭐
+    - **Idea**: Deception shows characteristic entropy inversions in logprob sequences
+    - **Epistemic status**: Theoretically sound, untested
+    - **MATS potential**: Very high - works with API-only access, no training needed
+    - **Key insight**: Truth cascades naturally; lies show entropy spike then commitment
+
+    #### 3. **Gradient Flow Dynamics** ⭐⭐⭐⭐
+    - **Idea**: Track gradient redistribution under interventions instead of static analysis
+    - **Epistemic status**: Strong theoretical basis from neuroscience
+    - **MATS potential**: High - novel approach, but requires full model access
+    - **Implementation**: Rank-1 LoRA perturbations + gradient tracking
+
+    #### 4. **Metabolic Cost of Deception** ⭐⭐⭐⭐
+    - **Idea**: Deception requires extra computation (higher gradient norms)
+    - **Epistemic status**: Moderate - based on neuroscience findings
+    - **MATS potential**: High if validated - could enable training-time interventions
+    - **Key metric**: `metabolic_cost = sum(torch.norm(grad) for grad in gradients)`
+
+    #### 5. **Multi-scale Temporal Analysis** ⭐⭐⭐
+    - **Idea**: Safety properties exist at different timescales (1-10, 10-100, 100+ tokens)
+    - **Epistemic status**: Speculative but grounded in neuroscience
+    - **MATS potential**: Medium - requires long context experiments
+    - **Application**: Wavelet decomposition of activation trajectories
+
+    #### 6. **Information Bottleneck for Safety** ⭐⭐⭐
+    - **Idea**: Safe models show monotonic information compression; deceptive models don't
+    - **Epistemic status**: Theoretical, needs validation
+    - **MATS potential**: Medium - elegant but may be hard to measure accurately
+    - **Implementation**: Track I(layer_n; output | input) across layers
+
+    ### Critical Warnings
+    1. **Interpretability theater**: Cherry-picked examples that don't generalize
+    2. **Dimensional delusion**: Any direction seems interpretable in high-D space
+    3. **Reductionism trap**: Complex systems resist component-level analysis
+
+    ### Key Unresolved Questions
+    - Where do models store memory/plans? (KV cache? Suppressed activations?)
+    - Can suppression patterns distinguish deception from honest mistakes?
+    - Do these methods work across model families and scales?
+
+    ### Most Actionable for MATS Researcher
+    Focus on **suppressed activation statistics** combined with **logprob dynamics** - this leverages existing work while adding novel unsupervised detection methods. The combination of internal (suppression) and external (logprobs) signals could yield robust deception detection without labeled data.
+
+    **Core insight**: Models' "guilty conscience" lives in what they suppress, not what they express.