AISC-Linear-Probe-Gen/paper_activations
Updated • 67
AI & ML interests
None defined yet.
AISC-Linear-Probe-Gen/deception_taxonomy_paper
Viewer • Updated • 57.6k • 774 • 1
AISC-Linear-Probe-Gen/obfuscated_activations
Updated • 92
AISC-Linear-Probe-Gen/deception-activations
Viewer • Updated • 14k • 24
AISC-Linear-Probe-Gen/sandbagging-activations
Preview • Updated • 182
AISC-Linear-Probe-Gen/sycophancy-activations
Preview • Updated • 30