INDEX
Explanations
references to individuals in pastoral roles
New Auto-Interp
Negative Logits
पत
-0.16
ARRIER
-0.15
ÑģÑĤен
-0.15
adesh
-0.15
uro
-0.14
å¤ķ
-0.14
kes
-0.14
asses
-0.13
_pad
-0.13
лоп
-0.13
POSITIVE LOGITS
agem
0.15
omba
0.15
okie
0.15
ÃŃda
0.14
cad
0.14
anova
0.14
fid
0.14
oba
0.14
borough
0.14
name
0.14
Activations Density 0.007%