INDEX
Explanations
references to executive actions taken by political leaders
New Auto-Interp
Negative Logits
Sob
-0.15
jes
-0.14
ippi
-0.14
ë³´ì¦Ŀê¸Ī
-0.14
uru
-0.14
sob
-0.14
copied
-0.13
리ìĬ¤
-0.13
ponents
-0.13
Dou
-0.13
POSITIVE LOGITS
branch
0.28
Branch
0.26
executive
0.26
branch
0.25
Executive
0.23
Branch
0.23
_branch
0.21
Executive
0.21
exec
0.20
-fi
0.19
Activations Density 0.014%