wassnameandClaudypoo 50bdf8d235 plot: automatic MFV foundation-emphasis map vs human cultures ...

MFV had only the dlogit dumbbell, no human comparison. Add plot_mfv_map: per-
foundation relative emphasis (z across foundations) of model base/+C/-C against
the 5 MFV human cultures (JimenezLeal+Yamada), z-scoring each profile so the
model's logit scale and humans' 1-5 wrongness compare by pattern. Social Norms
dropped (no human norm). Shows the model over-weights Care/Authority vs humans
and +C lowers Authority emphasis. Keeps the dumbbell too.

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

2026-06-25 07:33:42 +08:00

..

01_download.py

misc

2026-05-08 16:06:41 +08:00

02_rewrite.py

clean

2026-05-08 15:33:29 +08:00

02b_transcribe_ai_actor.py

clean

2026-05-08 16:14:07 +08:00

05_upload_hf.py

clean

2026-05-08 16:14:07 +08:00

06b_separation.py

clean

2026-05-08 16:14:07 +08:00

07_multilabel.py

forced-choice unification: drop legacy llm_/calibrated_, normalize human_*, justfile->09

2026-05-08 16:02:25 +08:00

07a_merge_labels.py

clean

2026-05-08 15:33:29 +08:00

09_forced_choice.py

Merge branch 'main' of https://github.com/wassname/tinymfv

2026-06-18 21:32:07 +08:00

plot_steer_showcase.py

plot: automatic MFV foundation-emphasis map vs human cultures

2026-06-25 07:33:42 +08:00

probe_mfv_think_budget.py

probe: add n_samples/temperature for BMA top1 test

2026-06-25 03:34:34 +08:00

probe_word_readout.py

add word-readout diagnostic (confirm validation-table 0.826 under old method)

2026-06-25 04:22:14 +08:00