INDEX
Negative Logits
ה
-1.09
OGND
-0.92
'\\;'
-0.91
Hentet
-0.89
myſelf
-0.85
EndGlobalSection
-0.84
AssemblyProduct
-0.81
Personensuche
-0.81
\}\\
-0.79
définiti
-0.79
POSITIVE LOGITS
is
0.53
N
0.48
ebus
0.47
R
0.45
trat
0.42
(
0.41
Is
0.41
3
0.40
'
0.40
can
0.40
Activations Density 0.099%