INDEX
Explanations
references to family relationships and parental figures
New Auto-Interp
Negative Logits
autorytatywna
-0.81
出版年
-0.78
styleType
-0.71
RenderAtEndOf
-0.66
Autoritní
-0.64
-0.63
createCanvas
-0.63
newswire
-0.62
первых
-0.61
PreferredItem
-0.61
POSITIVE LOGITS
families
0.55
parents
0.54
Económica
0.52
family
0.49
families
0.47
parents
0.47
Parents
0.47
dad
0.46
father
0.46
Parents
0.45
Activations Density 0.214%