INDEX
Negative Logits
s
-0.50
eri
-0.46
ague
-0.45
المتحدة
-0.45
sue
-0.45
accepte
-0.45
חיצוניים
-0.44
nera
-0.44
palio
-0.43
sr
-0.43
POSITIVE LOGITS
Rhestr
0.64
writeFieldEnd
0.57
Dispersion
0.54
extAlignment
0.53
WriteTagHelper
0.52
esModule
0.52
onCancelled
0.51
Executives
0.50
Toxicity
0.50
icrous
0.50
Activations Density 0.017%