INDEX
Explanations
words related to dairy products, especially cream
references to cream and creamy textures
New Auto-Interp
Negative Logits
vernment
-0.68
NF
-0.67
bably
-0.66
abama
-0.60
psychiat
-0.60
sbm
-0.58
FN
-0.58
stranger
-0.57
versive
-0.57
sec
-0.57
POSITIVE LOGITS
iness
1.08
ery
1.06
cup
1.02
erton
1.01
cheese
0.91
fields
0.88
bean
0.85
Sandwich
0.85
Cheese
0.82
maid
0.79
Activations Density 0.046%