INDEX
Explanations
mentions of specific names or titles, particularly those relevant to legal cases or individuals involved in them
New Auto-Interp
Negative Logits
iya
-0.17
ERG
-0.17
á»ĩ
-0.17
blick
-0.16
ukkit
-0.15
prung
-0.15
osta
-0.14
énom
-0.14
oria
-0.14
elts
-0.14
POSITIVE LOGITS
er
0.20
rang
0.18
ajs
0.16
put
0.16
sz
0.16
ajes
0.16
weed
0.16
PUT
0.15
ecer
0.15
تÙħاع
0.15
Activations Density 0.016%