INDEX
Explanations
references to parental and familial roles, particularly focusing on motherhood and family dynamics
New Auto-Interp
Negative Logits
nephew
-0.23
grandson
-0.21
Cousins
-0.18
niece
-0.17
granddaughter
-0.17
honeymoon
-0.16
cousin
-0.15
éĿĴå¹´
-0.15
hubby
-0.14
cousins
-0.14
POSITIVE LOGITS
mother
0.96
Mother
0.82
mothers
0.81
mother
0.78
Mother
0.78
mom
0.72
Mothers
0.66
moms
0.64
æ¯į亲
0.62
Mom
0.61
Activations Density 0.206%