INDEX
Explanations
mentions of various types of cheese
mentions of cheese and its specific types or references in food contexts
New Auto-Interp
Negative Logits
nant
-0.76
igious
-0.75
glim
-0.74
oday
-0.73
aylor
-0.69
uating
-0.68
ership
-0.67
ounces
-0.67
nce
-0.66
reads
-0.65
POSITIVE LOGITS
cloth
1.26
cheese
0.93
slic
0.90
ecake
0.90
fruit
0.86
weed
0.85
sandwich
0.84
bread
0.84
sauce
0.83
bowl
0.81
Activations Density 0.016%