timothee-chauvin's Stars
callummcdougall/ARENA_3.0
niklasrisse/TopScoreWrongExam
CentreSecuriteIA/BELLS
Benchmarks for the Evaluation of LLM Supervision
ArjunPanickssery/the_vs_my
Prompt LLMs for feedback on "the" and not "my" code/response/essay/etc for more critical feedback
js-d/bongard
CVEProject/cvelistV5
CVE cache of the official CVE List in CVE JSON 5 format
METR/task-standard
METR Task Standard
TransformerLensOrg/TransformerLens
A library for mechanistic interpretability of GPT-style language models