siddharthmb
/

multiagent-verification-probes

interpretability

Model card Files Files and versions

multiagent-verification-probes / exp5 /probes

22.4 MB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

siddharthmb's picture

Upload probes, handles, and attention diagnostics (part 4)

7dd5159 verified 20 days ago

gold_first_blind
Upload probes, handles, and attention diagnostics (part 2) 20 days ago
gold_first_told
Upload probes, handles, and attention diagnostics (part 3) 20 days ago
strong_first_blind
Upload probes, handles, and attention diagnostics (part 3) 20 days ago
strong_first_told
Upload probes, handles, and attention diagnostics (part 4) 20 days ago