INDEX
Explanations
geographical locations, specifically in Wisconsin
references to the state of Wisconsin
New Auto-Interp
Negative Logits
ion
-0.80
inant
-0.77
izoph
-0.74
icably
-0.74
ainer
-0.73
ourge
-0.72
izers
-0.71
inators
-0.70
angelo
-0.68
inates
-0.68
POSITIVE LOGITS
manship
0.95
pered
0.91
Wis
0.88
eman
0.86
pering
0.85
WI
0.74
gets
0.73
Fed
0.71
isconsin
0.68
Pis
0.68
Activations Density 0.056%