INDEX
Explanations
mentions or references to chicken and related terms
mentions of chicken
New Auto-Interp
Negative Logits
orsche
-0.90
raints
-0.80
oppable
-0.78
INAL
-0.78
BLIC
-0.74
ilitarian
-0.74
ilities
-0.74
anchester
-0.73
unci
-0.71
ibel
-0.71
POSITIVE LOGITS
pox
1.15
breasts
0.92
manure
0.90
thighs
0.87
wings
0.86
meat
0.86
hawk
0.84
bones
0.84
food
0.83
fish
0.83
Activations Density 0.024%