wassnameandClaudypoo 74e21552af nbs/steering_demo: dual-gate results + sig-fig table + Claude qualitative read ...

Regenerated over 7 methods with the dual-gate edge. Finding is NEGATIVE: none flip
the deliberated YES/NO within the answer-alive budget (swings noise-level <=0.06 vs
random 0.03, baseline 0.107; promoted tokens are junk not lie/honest). word's 0.97
swing is a dead-answer artifact (ans_mass 0.14), correctly nulled by score. Notebook
adds the sig-fig comparison table and a per-method qualitative cell authored from the
real generations.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

2026-07-12 16:29:46 +08:00

..

eval_mechanisms.txt

docs: overnight mechanism report -- persona_topk works, rubric was mismeasured, dilemma demo proposal

2026-07-11 22:16:24 +08:00

measure_all.jsonl

docs: corrected dilemma findings -- persona_pinv the robust standout, big shifts were artifacts

2026-07-12 07:57:20 +08:00

steering_demo_results.json

nbs/steering_demo: dual-gate results + sig-fig table + Claude qualitative read

2026-07-12 16:29:46 +08:00