INDEX
Explanations
references to religious texts or scripture
New Auto-Interp
Negative Logits
FunctionFlags
-0.56
ddelweddau
-0.55
[*]
-0.55
ireo
-0.54
vulgaires
-0.53
ighted
-0.53
altro
-0.53
дравствуйте
-0.53
initro
-0.52
Adapun
-0.51
POSITIVE LOGITS
lossians
1.03
iastes
0.89
محفوظة
0.68
Normdatei
0.65
Psalm
0.64
Corinthians
0.64
gouver
0.63
xodo
0.61
StatelessWidget
0.61
Hebrews
0.60
Activations Density 0.089%