INDEX
Explanations
ingredients, food items, and cooking instructions related to a recipe, with a specific emphasis on bacon
New Auto-Interp
Negative Logits
ept
-0.76
heny
-0.71
cases
-0.69
oric
-0.69
inen
-0.67
ppelin
-0.66
lasses
-0.64
hips
-0.62
Gaia
-0.61
iazep
-0.61
POSITIVE LOGITS
nect
1.06
grease
1.06
halla
0.97
chees
0.89
bacon
0.80
wallet
0.79
sandwich
0.75
fruit
0.73
netflix
0.73
foil
0.71
Activations Density 0.043%