INDEX
Explanations
proper nouns related to individuals named Anton
mentions of the name "Anton"
New Auto-Interp
Negative Logits
glers
-0.90
Kit
-0.81
tto
-0.77
FU
-0.77
Pokemon
-0.73
blems
-0.73
olkien
-0.72
PLE
-0.71
ciples
-0.71
Complete
-0.69
POSITIVE LOGITS
igan
0.83
а
0.78
igans
0.77
iard
0.77
Anton
0.76
iques
0.76
о
0.74
inite
0.74
assian
0.73
oids
0.73
Activations Density 0.027%