lasrprobegen/deception-activations
Viewer • Updated • 14k • 27 • 2
LASR Probe Gen
university
AI & ML interests
None defined yet.
lasrprobegen/authority-activations
Viewer • Updated • 120k • 26
lasrprobegen/sycophancy-activations
Viewer • Updated • 143k • 148
lasrprobegen/refusal-activations
Viewer • Updated • 10.2k • 397 • 1
lasrprobegen/science-activations
Preview • Updated • 37
lasrprobegen/metaphors-activations
Preview • Updated • 46
lasrprobegen/lists-activations
Preview • Updated • 3.1k
lasrprobegen/sandbagging-activations
Preview • Updated • 29