INDEX
Explanations
references to familial relationships and ancestry
New Auto-Interp
Negative Logits
Obrázky
-0.50
Anſ
-0.47
Inſ
-0.43
erw
-0.42
calendriers
-0.42
Perſ
-0.42
Umfang
-0.41
veo
-0.41
Soma
-0.40
şek
-0.40
POSITIVE LOGITS
parents
0.63
contentLoaded
0.54
grandparents
0.52
genitori
0.52
mother
0.51
mom
0.50
pinulongan
0.50
father
0.50
parental
0.48
Parents
0.48
Activations Density 0.175%