INDEX
Explanations
elements related to women's empowerment and equality
New Auto-Interp
Negative Logits
.dp
-0.14
abant
-0.14
punkt
-0.14
оваÑĢи
-0.14
BUR
-0.14
odash
-0.14
γλη
-0.14
_redirected
-0.14
Kurt
-0.13
ì¹Ļ
-0.13
POSITIVE LOGITS
unde
0.15
rang
0.15
ua
0.15
Brennan
0.14
uhn
0.14
обÑĢаз
0.13
ibu
0.13
un
0.13
Balls
0.13
rahim
0.13
Activations Density 0.173%