INDEX
Explanations
titles and roles associated with government officials
New Auto-Interp
Negative Logits
stead
-0.19
ilt
-0.18
orro
-0.16
tam
-0.15
jun
-0.15
#Region
-0.15
st
-0.15
ê
-0.14
APS
-0.14
ILT
-0.14
POSITIVE LOGITS
ship
0.19
æ¸Ī
0.17
ships
0.17
embre
0.16
minded
0.16
MBER
0.16
istrovstvÃŃ
0.14
ible
0.14
znik
0.14
962
0.14
Activations Density 0.016%