lasrprobegen/deception-activations
Viewer • Updated • 14k • 302 • 2
LASR Probe Gen
university
AI & ML interests
None defined yet.
lasrprobegen/authority-activations
Viewer • Updated • 120k • 47
lasrprobegen/sycophancy-activations
Viewer • Updated • 143k • 360
lasrprobegen/refusal-activations
Viewer • Updated • 10.2k • 772 • 1
lasrprobegen/science-activations
Preview • Updated • 36
lasrprobegen/metaphors-activations
Preview • Updated • 130
lasrprobegen/lists-activations
Preview • Updated • 280
lasrprobegen/sandbagging-activations
Preview • Updated • 75