INDEX
Explanations
discussions or analysis within a political context
New Auto-Interp
Negative Logits
ens
-0.73
ensible
-0.69
SHARES
-0.67
ĸļ
-0.66
,''
-0.66
uits
-0.66
!",
-0.65
azel
-0.65
etheus
-0.65
''.
-0.65
POSITIVE LOGITS
whereas
0.96
Conversely
0.84
others
0.81
Others
0.78
Whereas
0.73
Likewise
0.70
Similarly
0.68
secondly
0.68
Anon
0.67
followed
0.66
Activations Density 0.814%