INDEX
Explanations
references to the name "Johnny."
references to the name "Johnny" and related entities
New Auto-Interp
Negative Logits
hips
-0.88
ered
-0.83
uration
-0.83
itect
-0.82
oral
-0.80
raints
-0.78
inarily
-0.78
scl
-0.78
lain
-0.77
ipation
-0.77
POSITIVE LOGITS
Manziel
0.96
Yong
0.88
ppo
0.78
Bravo
0.77
Boy
0.75
Cash
0.75
Rico
0.73
Sins
0.72
bum
0.72
Cage
0.72
Activations Density 0.015%