INDEX
Explanations
mentions of a specific person named Andy
the presence of the name "Andy" in various contexts
New Auto-Interp
Negative Logits
hips
-0.96
maid
-0.81
ingen
-0.81
nces
-0.78
porting
-0.73
inals
-0.72
olid
-0.71
cffff
-0.70
iotic
-0.69
lled
-0.67
POSITIVE LOGITS
Dalton
0.80
Weir
0.75
Cohen
0.74
Neil
0.74
visors
0.73
Coul
0.73
Andy
0.72
Murray
0.71
Kaufman
0.71
anut
0.70
Activations Density 0.012%