lasrprobegen/deception-activations
Viewer • Updated • 14k • 758 • 1
LASR Probe Gen
university
AI & ML interests
None defined yet.
models 0
None public yet
datasets 8
lasrprobegen/authority-activations
Viewer • Updated • 120k • 167
lasrprobegen/sycophancy-activations
Viewer • Updated • 143k • 1.01k
lasrprobegen/refusal-activations
Viewer • Updated • 10.2k • 1.85k • 1
lasrprobegen/science-activations
Preview • Updated • 461
lasrprobegen/metaphors-activations
Preview • Updated • 176
lasrprobegen/lists-activations
Preview • Updated • 412
lasrprobegen/sandbagging-activations
Preview • Updated • 98