INDEX
Explanations
references to political and societal issues and events
New Auto-Interp
Negative Logits
Eleven
-0.86
CCC
-0.77
paragraph
-0.68
Amen
-0.66
////////////////////////////////
-0.64
Globe
-0.63
Rating
-0.63
Sao
-0.62
Club
-0.62
CLASSIFIED
-0.61
POSITIVE LOGITS
're
1.39
've
1.12
'll
1.07
selves
0.99
'd
0.95
selves
0.91
zbollah
0.84
shouldn
0.78
themselves
0.78
pherd
0.77
Activations Density 18.707%