INDEX
Explanations
food ingredients and their descriptions
New Auto-Interp
Negative Logits
519
-0.15
chem
-0.15
raq
-0.14
ARN
-0.14
619
-0.14
946
-0.14
813
-0.14
Schultz
-0.14
jet
-0.14
iaux
-0.14
POSITIVE LOGITS
skins
0.19
skins
0.19
juice
0.17
skin
0.16
erot
0.16
-shaped
0.15
Skin
0.15
skin
0.15
-centered
0.15
/apple
0.15
Activations Density 0.057%