INDEX
Explanations
mentions of a specific individual, particularly with the name "Giunta."
New Auto-Interp
Negative Logits
שוליים
-0.91
Arbe
-0.79
nergy
-0.71
Ketten
-0.68
araw
-0.68
Reiche
-0.66
Harn
-0.66
Seel
-0.66
Trost
-0.66
Ural
-0.65
POSITIVE LOGITS
Gi
1.62
gi
1.46
Gi
1.45
Giuliani
1.22
GIP
1.18
Giordano
1.14
Giuli
1.13
gi
1.07
GI
1.05
Gis
1.00
Activations Density 0.015%