INDEX
Explanations
names of individuals or proper nouns related to people and events
New Auto-Interp
Negative Logits
alama
-0.17
749
-0.16
.CompareTag
-0.15
öz
-0.15
ùi
-0.15
apore
-0.15
agem
-0.14
peed
-0.14
itet
-0.14
islav
-0.14
POSITIVE LOGITS
adiens
0.14
arians
0.14
zer
0.13
anzi
0.13
.scalablytyped
0.13
κι
0.13
WindowTitle
0.13
lesh
0.13
isc
0.13
ustral
0.13
Activations Density 0.205%