INDEX
Explanations
topics related to abortion and bipartisan political discussions
New Auto-Interp
Negative Logits
allen
-0.16
491
-0.15
vic
-0.15
insky
-0.15
.paper
-0.15
_preference
-0.14
owitz
-0.14
leston
-0.14
Ches
-0.14
gars
-0.14
POSITIVE LOGITS
alike
0.19
Carr
0.16
iesel
0.16
Nolan
0.15
ór
0.15
ker
0.14
лав
0.14
imon
0.14
ê³µ
0.14
PRESSION
0.14
Activations Density 0.163%