lasrprobegen/deception-activations
Viewer
•
Updated
•
14k
•
401
•
1
LASR Probe Gen
university
AI & ML interests
None defined yet.
Recent Activity
models
0
None public yet
datasets
8
lasrprobegen/authority-activations
Viewer
•
Updated
•
120k
•
1.56k
lasrprobegen/sycophancy-activations
Viewer
•
Updated
•
143k
•
3k
lasrprobegen/refusal-activations
Viewer
•
Updated
•
10.2k
•
3.76k
•
1
lasrprobegen/science-activations
Preview
•
Updated
•
1.78k
lasrprobegen/metaphors-activations
Preview
•
Updated
•
2.18k
lasrprobegen/lists-activations
Preview
•
Updated
•
907
lasrprobegen/sandbagging-activations
Preview
•
Updated
•
364