INDEX
Explanations
proper nouns such as names
mentions of prominent individuals, particularly those with the title "Mr."
New Auto-Interp
Negative Logits
actionGroup
-0.85
··
-0.76
\">
-0.71
phia
-0.71
Ô
-0.71
LET
-0.69
appre
-0.69
rawdownloadcloneembedreportprint
-0.68
STD
-0.67
ASED
-0.65
POSITIVE LOGITS
Claus
0.78
Turnbull
0.75
Farage
0.74
Obama
0.74
Justice
0.73
Hague
0.73
Hyde
0.73
Bah
0.71
Finn
0.70
orm
0.69
Activations Density 0.034%