INDEX
Explanations
words related to a specific person named Hunter
mentions of specific character names from a franchise
New Auto-Interp
Negative Logits
orship
-0.92
ible
-0.91
iment
-0.89
ichick
-0.87
urable
-0.86
raints
-0.86
acies
-0.86
ions
-0.86
urities
-0.82
ibilities
-0.80
POSITIVE LOGITS
Beer
0.79
esses
0.72
llan
0.71
¯¯¯¯
0.70
custod
0.65
Burnett
0.65
Rover
0.64
bard
0.64
dams
0.62
Feldman
0.60
Activations Density 0.124%