INDEX
Explanations
mentions of Donald Trump
New Auto-Interp
Negative Logits
.WinForms
-0.15
//---------------------------------------------------------------------------↵↵
-0.15
kills
-0.14
anes
-0.14
ëģĶ
-0.14
lobal
-0.14
plug
-0.14
idal
-0.14
yar
-0.14
¸ı
-0.14
POSITIVE LOGITS
son
0.32
Trump
0.25
SON
0.24
sons
0.23
sonian
0.20
Trump
0.20
Duck
0.19
trump
0.18
du
0.18
nelly
0.17
Activations Density 0.007%