INDEX
Explanations
mentions of family members, especially children
references to family structures and relationships
New Auto-Interp
Negative Logits
zsche
-0.70
obin
-0.67
guiName
-0.67
Trend
-0.65
Sequence
-0.65
urden
-0.62
captcha
-0.61
itself
-0.61
abus
-0.59
matter
-0.59
POSITIVE LOGITS
daughters
1.63
sons
1.48
grandchildren
1.39
children
1.26
siblings
1.18
kids
1.17
girlfriends
1.13
sisters
1.11
wives
1.11
dogs
1.10
Activations Density 0.097%