INDEX
Explanations
words related to baking bread or similar dough products
references to bread in various contexts
New Auto-Interp
Negative Logits
uate
-0.83
ities
-0.76
uated
-0.74
uating
-0.70
Cheong
-0.68
vernment
-0.64
igious
-0.62
Bieber
-0.62
Oro
-0.61
Amph
-0.61
POSITIVE LOGITS
sticks
1.20
fruit
1.20
cr
1.20
winner
1.13
grain
1.06
wallet
1.05
pudding
1.01
nut
0.98
nuts
0.97
wich
0.95
Activations Density 0.033%