INDEX
Explanations
references to female subjects or entities
New Auto-Interp
Negative Logits
Ewa
-0.78
———
-0.77
Barbuda
-0.75
rootReducer
-0.75
Ή
-0.73
Quell
-0.72
Roswell
-0.72
нига
-0.71
Barrett
-0.70
stdc
-0.69
POSITIVE LOGITS
ladies
1.08
ladies
1.03
Ladies
1.00
lady
0.94
Ladies
0.92
للاسماء
0.91
soever
0.82
httphttps
0.82
ţii
0.82
LADY
0.81
Activations Density 0.208%