INDEX
Explanations
people and their relationships
mentions of female people—she/her subjects, women’s roles or names—especially in intimate, relational, or caregiving contexts.
New Auto-Interp
Negative Logits
round
0.33
tres
0.31
அந்த
0.31
بندی
0.30
|_
0.30
候
0.30
Error
0.30
潜在
0.29
aureus
0.29
%}
0.28
POSITIVE LOGITS
boyfriend
0.47
আমাকে
0.45
让我
0.43
insisting
0.43
Boyfriend
0.42
insisted
0.41
hubby
0.41
insist
0.40
fiancé
0.40
讓我
0.40
Activations Density 0.227%