INDEX
Explanations
references to political titles and positions
New Auto-Interp
Negative Logits
uye
-0.15
edm
-0.15
ayo
-0.15
glas
-0.15
FP
-0.15
anio
-0.15
_isr
-0.14
oo
-0.14
lesh
-0.14
_FC
-0.14
POSITIVE LOGITS
ollar
0.15
bett
0.15
fitte
0.15
Prog
0.14
à¸į
0.14
achel
0.14
-elect
0.13
SSION
0.13
ayment
0.13
.byte
0.13
Activations Density 0.028%