INDEX
Explanations
mentions of the brand "Gatorade"
the suffix "ade" in words
New Auto-Interp
Negative Logits
ipeg
-0.80
nep
-0.76
ullivan
-0.69
urally
-0.68
atem
-0.68
urers
-0.66
kefeller
-0.66
ship
-0.65
ilogy
-0.65
enegger
-0.64
POSITIVE LOGITS
lled
0.91
rers
0.85
rer
0.83
hyde
0.78
away
0.77
ragon
0.77
ga
0.77
lda
0.77
pee
0.77
llan
0.76
Activations Density 0.019%