INDEX
Explanations
tokens that represent various food items and related categories
New Auto-Interp
Negative Logits
otherwise
-0.18
Otherwise
-0.16
ãĤ¨
-0.15
ÐŃ
-0.15
Ñį
-0.15
FE
-0.15
"encoding
-0.14
.decor
-0.14
dollar
-0.14
_FD
-0.14
POSITIVE LOGITS
G
0.15
gece
0.15
H
0.15
"g
0.15
Health
0.15
Geile
0.14
GRAT
0.14
gh
0.14
Gloss
0.14
.googleapis
0.14
Activations Density 0.054%