INDEX
Explanations
references to women in the context of implications for fertility and reproduction
New Auto-Interp
Negative Logits
1
-1.84
1
-1.03
১
-0.95
১
-0.84
१
-0.83
١
-0.73
१
-0.72
١
-0.71
¹
-0.69
₁
-0.68
POSITIVE LOGITS
يتيمه
0.64
۴
0.63
InjectAttribute
0.62
۶
0.62
fün
0.60
۷
0.60
SEVEN
0.59
۵
0.58
۸
0.57
fifth
0.56
Activations Density 1.359%