INDEX
Explanations
references to religious affiliations and organizations
New Auto-Interp
Negative Logits
مشين
-0.59
MLLoader
-0.56
estekak
-0.51
\{\\-0.50
matchCondition
-0.50
idio
-0.48
kozások
-0.48
emble
-0.48
MeasureSpec
-0.47
AutoresizingMask
-0.46
POSITIVE LOGITS
católica
0.76
catholique
0.73
Catholic
0.72
Catholic
0.65
katholischen
0.62
paroisse
0.60
Catholics
0.57
kathol
0.57
reciclado
0.55
reciclaje
0.54
Activations Density 0.160%