INDEX
Explanations
mentions of the city of Liverpool
New Auto-Interp
Negative Logits
racite
-0.44
eraard
-0.42
ابقة
-0.41
woordig
-0.41
Стан
-0.40
c
-0.40
נד
-0.40
&
-0.40
Cha
-0.40
"
-0.39
POSITIVE LOGITS
Liverpool
1.16
Liverpool
1.06
liverpool
0.88
LIVER
0.77
Liver
0.73
Liver
0.68
Autoritní
0.65
liver
0.64
فريبيس
0.63
DockStyle
0.63
Activations Density 0.001%