INDEX
Explanations
phrases related to family members, especially mothers
New Auto-Interp
Negative Logits
enhagen
-0.85
sidx
-0.77
espie
-0.76
iannopoulos
-0.73
Players
-0.73
uden
-0.72
raltar
-0.72
udo
-0.71
Players
-0.70
leck
-0.68
POSITIVE LOGITS
herself
1.89
pregnant
1.51
husband
1.28
womb
1.27
maid
1.26
maiden
1.23
menstru
1.23
childbirth
1.22
pregnancy
1.21
boyfriend
1.18
Activations Density 0.600%