INDEX
Explanations
mentions of women's roles and relationships in familial and social contexts
New Auto-Interp
Negative Logits
akit
-0.17
大人
-0.15
RowCount
-0.15
Franç
-0.14
664
-0.14
ÏĦοÏĤ
-0.14
erin
-0.14
Smarty
-0.14
byss
-0.13
ulet
-0.13
POSITIVE LOGITS
sons
0.43
mothers
0.41
fathers
0.37
daughters
0.37
brothers
0.35
sisters
0.34
Mothers
0.34
Sons
0.33
sons
0.31
wives
0.30
Activations Density 0.024%