INDEX
Explanations
mentions of the word "baby"
references to babies
New Auto-Interp
Negative Logits
pmwiki
-0.87
SPONSORED
-0.79
orial
-0.79
atility
-0.78
ictional
-0.76
âķIJ
-0.74
encing
-0.74
opol
-0.73
ATIONS
-0.72
atism
-0.72
POSITIVE LOGITS
metal
0.91
doll
0.87
babies
0.82
girl
0.81
boy
0.81
daddy
0.81
dolls
0.79
girl
0.79
hood
0.78
baby
0.78
Activations Density 0.022%