katanastas
/

llm-guardrails-probing

interpretability

content-moderation

logistic-regression

Model card Files Files and versions

llm-guardrails-probing / .gitattributes

Commit History

Upload images/21_guard_vs_probe_perclass.png with huggingface_hub

23c4d15
verified

katanastas commited on May 19

Upload images/20_guard_vs_probe_confusion.png with huggingface_hub

cf51e46
verified

katanastas commited on May 19

Upload images/16_guard_vs_probe.png with huggingface_hub

6edd450
verified

katanastas commited on May 19

initial commit

e02b7d0
verified

katanastas commited on May 18