INDEX
Explanations
references to 'Baby' as a term of affection or as part of consumer branding
New Auto-Interp
Negative Logits
ictional
-0.91
idency
-0.77
ional
-0.77
iction
-0.76
ript
-0.76
atively
-0.74
orial
-0.73
iance
-0.72
ulty
-0.72
ahime
-0.71
POSITIVE LOGITS
metal
1.17
Baby
0.92
Daddy
0.92
Doll
0.88
cakes
0.87
Steps
0.83
Center
0.82
Baby
0.81
Driver
0.79
Mama
0.79
Activations Density 0.011%