INDEX
Explanations
words related to politicians and legislative bodies
references to the Knesset and related entities
New Auto-Interp
Negative Logits
ributes
-0.69
vier
-0.68
ttes
-0.68
Boll
-0.67
oute
-0.65
rique
-0.65
ous
-0.63
Nose
-0.62
isks
-0.62
iere
-0.61
POSITIVE LOGITS
ignt
0.85
NetMessage
0.82
ILCS
0.75
eneg
0.65
FORM
0.65
ikarp
0.64
ãĤ±
0.63
atan
0.63
gap
0.63
therap
0.63
Activations Density 0.098%