INDEX
Explanations
references to relationships and gender dynamics, particularly focusing on women and their roles
female pronouns and women
New Auto-Interp
Negative Logits
UnsafeEnabled
-0.61
noDo
-0.58
sizeCache
-0.57
MigrationBuilder
-0.56
виправивши
-0.55
ویکیآمباردا
-0.52
ActionCreators
-0.51
僕
-0.51
僕も
-0.49
僕は
-0.48
POSITIVE LOGITS
Obrigada
0.55
Women
0.51
ค่ะ
0.48
Women
0.48
Woman
0.41
łam
0.39
kadın
0.38
Beijos
0.38
ftagPool
0.36
Попис
0.36
Activations Density 0.280%