INDEX
Explanations
proper nouns related to names or titles
mentions of the name "Gray."
New Auto-Interp
Negative Logits
=-=-
-1.01
uador
-0.89
olkien
-0.88
orship
-0.87
urally
-0.86
ificial
-0.85
adena
-0.84
ession
-0.83
urities
-0.81
ulhu
-0.80
POSITIVE LOGITS
hound
1.04
fur
0.99
claw
0.90
lings
0.87
wolf
0.86
Gray
0.85
hawk
0.83
Matter
0.82
ling
0.80
beard
0.80
Activations Density 0.010%