INDEX
Explanations
mentions of breast milk
references to breast milk and related topics
New Auto-Interp
Negative Logits
upon
-0.74
umar
-0.74
Amend
-0.72
vernment
-0.71
arta
-0.69
NRS
-0.67
eff
-0.66
ADRA
-0.66
Bravo
-0.65
inez
-0.63
POSITIVE LOGITS
bone
1.06
breast
1.04
plate
1.02
breasts
0.96
milk
0.92
implants
0.91
fed
0.90
nipples
0.82
nipple
0.81
cancer
0.80
Activations Density 0.006%