INDEX
Explanations
proper nouns related to a specific location named "Butler."
mentions of the name "Butler."
New Auto-Interp
Negative Logits
light
-0.84
itives
-0.84
arin
-0.80
clud
-0.79
lighting
-0.77
ularity
-0.77
udo
-0.76
¯¯¯¯
-0.74
rament
-0.74
atives
-0.72
POSITIVE LOGITS
ipop
0.82
phia
0.78
psey
0.74
ivari
0.70
Butler
0.67
NOTICE
0.67
flies
0.66
Mash
0.65
McH
0.65
ucky
0.64
Activations Density 0.054%