INDEX
Explanations
mentions of the United States
New Auto-Interp
Negative Logits
Efq
-0.71
NSCoder
-0.68
متعلقه
-0.67
myſelf
-0.63
itſelf
-0.61
poffe
-0.59
whoſe
-0.59
mergeFrom
-0.57
reaſon
-0.56
sidemargin
-0.56
POSITIVE LOGITS
States
1.15
Kingdom
0.87
Nations
0.83
United
0.83
States
0.80
states
0.79
STATES
0.78
United
0.71
kingdom
0.69
Kingdom
0.69
Activations Density 0.079%