INDEX
Explanations
references to personal experiences and motherhood
New Auto-Interp
Negative Logits
masturb
-0.16
ارج
-0.15
åIJĮåѦ
-0.14
éϵ
-0.14
engin
-0.14
hoÅŁ
-0.14
åĪº
-0.13
dÃŃv
-0.13
qrt
-0.13
ì²Ń
-0.13
POSITIVE LOGITS
raising
0.32
mother
0.31
paren
0.29
parenting
0.28
Paren
0.28
mom
0.25
Parent
0.24
parent
0.23
paren
0.23
mother
0.22
Activations Density 0.130%