INDEX
Explanations
mentions of specific types of dishes or food ingredients
New Auto-Interp
Negative Logits
âĢ¢âĢ¢âĢ¢âĢ¢
-0.75
SPONSORED
-0.69
Stories
-0.68
BLIC
-0.64
Sharing
-0.64
olicy
-0.63
ly
-0.63
REP
-0.63
VICE
-0.63
rik
-0.62
POSITIVE LOGITS
urgical
1.07
mith
1.06
ighting
1.05
ayer
1.04
pace
1.02
pha
0.96
pine
0.95
anguage
0.94
aurus
0.94
creen
0.94
Activations Density 0.007%