INDEX
Explanations
the presence of nationalities or ethnicities related to individuals mentioned in the text
New Auto-Interp
Negative Logits
ekil
-0.17
ksen
-0.16
hsi
-0.16
onso
-0.15
uv
-0.14
fully
-0.14
mpp
-0.14
astics
-0.14
allet
-0.14
oice
-0.14
POSITIVE LOGITS
.byId
0.16
_NT
0.15
Miner
0.14
ogens
0.14
ahren
0.14
ãĤĩ
0.14
EDURE
0.13
кан
0.13
ÑĢод
0.13
®
0.13
Activations Density 0.166%