INDEX
Explanations
mentions of the state of Connecticut
mentions of the state of Connecticut
New Auto-Interp
Negative Logits
andr
-0.70
eting
-0.70
wagen
-0.69
ĺħ
-0.68
pora
-0.68
cules
-0.67
cles
-0.66
vel
-0.66
cca
-0.66
haps
-0.66
POSITIVE LOGITS
icut
1.04
Connecticut
0.89
Yankee
0.88
ivity
0.83
swick
0.79
igan
0.76
aught
0.75
Rapids
0.75
Devils
0.73
oslov
0.72
Activations Density 0.024%