INDEX
Explanations
mentions of the letter 'b'
New Auto-Interp
Negative Logits
Magikarp
-0.66
Porsche
-0.64
Lear
-0.60
departure
-0.59
eyebrow
-0.58
Gutenberg
-0.57
snail
-0.56
insidious
-0.56
nomine
-0.56
Lauder
-0.56
POSITIVE LOGITS
rief
1.14
odies
1.13
rities
1.10
iotics
1.06
attery
1.05
ilib
1.04
ionic
1.04
ilingual
1.04
iotic
1.03
ilateral
1.03
Activations Density 0.018%