INDEX
Explanations
mentions of the name "Kirov" and related terms
occurrences of the term "Kiro."
New Auto-Interp
Negative Logits
ervative
-0.96
iple
-0.75
orthern
-0.73
ennett
-0.72
enberg
-0.71
ŃĶ
-0.71
itutional
-0.68
ingham
-0.68
ourage
-0.67
Ö¼
-0.66
POSITIVE LOGITS
zzi
1.16
phant
1.10
tto
1.01
zes
0.89
tti
0.88
IDS
0.84
vable
0.84
lette
0.82
dden
0.82
tes
0.80
Activations Density 0.014%