INDEX
Explanations
mentions of chocolate and related flavors or ingredients
New Auto-Interp
Negative Logits
osaur
-0.19
-State
-0.16
ãĥ¥ãĥ¼
-0.16
íĥľ
-0.16
uter
-0.16
lue
-0.15
ities
-0.15
dn
-0.15
memberof
-0.15
hetto
-0.15
POSITIVE LOGITS
chip
0.27
Chip
0.25
chip
0.25
y
0.24
CHIP
0.23
Chip
0.22
-covered
0.22
CHIP
0.21
chips
0.18
_chip
0.18
Activations Density 0.004%