INDEX
Explanations
politicians' names and titles
references to Democratic party members or representatives
New Auto-Interp
Negative Logits
ãĤ¡
-0.80
éĹĺ
-0.79
ãĤ¤ãĥĪ
-0.75
Bulg
-0.73
terday
-0.72
Nun
-0.70
zai
-0.68
Pastebin
-0.65
ItemTracker
-0.65
Remem
-0.65
POSITIVE LOGITS
olph
1.08
etermin
1.07
ownt
1.06
ynam
1.05
etermination
1.04
rown
1.02
ynasty
1.01
ried
1.01
ollar
0.98
iscovery
0.98
Activations Density 0.043%