INDEX
Explanations
references to people with former, current, or significant roles in various organizations, particularly in sports or government
New Auto-Interp
Negative Logits
á»±c
-0.15
ovah
-0.15
Mob
-0.14
даÑĤÑĮ
-0.14
ruk
-0.14
/Core
-0.14
elow
-0.14
isson
-0.14
=center
-0.14
udeau
-0.14
POSITIVE LOGITS
tom
0.17
IDD
0.16
evid
0.15
usleep
0.15
spat
0.15
ÑĮ
0.15
058
0.14
697
0.14
768
0.14
mis
0.14
Activations Density 0.078%