lasrprobegen/deception-activations
Viewer
•
Updated
•
14k
•
375
•
1
LASR Probe Gen
university
AI & ML interests
None defined yet.
Recent Activity
lasrprobegen/authority-activations
Viewer
•
Updated
•
120k
•
1.44k
lasrprobegen/sycophancy-activations
Viewer
•
Updated
•
143k
•
2.6k
lasrprobegen/refusal-activations
Viewer
•
Updated
•
10.2k
•
3.67k
•
1
lasrprobegen/science-activations
Preview
•
Updated
•
1.39k
lasrprobegen/metaphors-activations
Preview
•
Updated
•
1.97k
lasrprobegen/lists-activations
Preview
•
Updated
•
661
lasrprobegen/sandbagging-activations
Preview
•
Updated
•
313