INDEX
Explanations
references to law enforcement personnel or officers
New Auto-Interp
Negative Logits
¢åįķ
-0.16
+offset
-0.16
Äł
-0.15
ترÛĮ
-0.15
wit
-0.15
âĢĮب
-0.15
ستاÙĨ
-0.14
:host
-0.14
ĥĿ
-0.14
tele
-0.14
POSITIVE LOGITS
portun
0.17
ivec
0.17
hip
0.15
eneg
0.15
enschaft
0.15
ettes
0.15
elik
0.14
hood
0.14
NS
0.14
rend
0.14
Activations Density 0.010%