INDEX
Explanations
mentions of Donald Trump and Barack Obama in the context of political discussions
New Auto-Interp
Negative Logits
mae
-0.15
nici
-0.15
jal
-0.15
è¶
-0.15
лиÑĨ
-0.15
ãģ¾ãģ¾
-0.14
cms
-0.14
horn
-0.14
niche
-0.14
GRA
-0.14
POSITIVE LOGITS
δι
0.16
Matthias
0.16
exh
0.15
.disc
0.15
íĨ
0.15
yer
0.15
filer
0.15
TreeWidgetItem
0.14
매
0.14
alon
0.14
Activations Density 0.039%