INDEX
Explanations
mentions of the name "Tony" or related prominent figures
New Auto-Interp
Negative Logits
lasses
-0.84
ornia
-0.79
orders
-0.78
milo
-0.73
llor
-0.72
ħ
-0.72
sg
-0.71
everal
-0.71
scl
-0.71
¬¼
-0.70
POSITIVE LOGITS
neau
1.05
ista
0.99
ople
0.85
Spurs
0.85
ahime
0.79
ographed
0.74
zai
0.74
omics
0.70
nel
0.69
aldo
0.69
Activations Density 0.104%