INDEX
Explanations
relationships involving infidelity and emotional conflicts
New Auto-Interp
Negative Logits
Husband
-0.21
husband
-0.20
husbands
-0.19
ä¸Ī夫
-0.18
hus
-0.16
夫
-0.15
onaut
-0.15
æĬľ
-0.15
sex
-0.15
ander
-0.14
POSITIVE LOGITS
whom
0.18
younger
0.17
herits
0.15
afar
0.15
unavailable
0.15
enci
0.15
objet
0.15
his
0.15
ixa
0.15
objeto
0.14
Activations Density 0.217%