INDEX
Explanations
references to the state of Wisconsin
references to Wisconsin
New Auto-Interp
Negative Logits
angular
-0.78
obyl
-0.76
rained
-0.71
razen
-0.70
ruct
-0.70
rices
-0.68
onial
-0.68
eon
-0.65
ronic
-0.65
Ferdinand
-0.65
POSITIVE LOGITS
Rapids
0.94
Wisconsin
0.90
waukee
0.89
Madison
0.86
WI
0.83
kers
0.81
Wisconsin
0.79
manship
0.77
ites
0.76
Bad
0.75
Activations Density 0.042%