INDEX
Explanations
references to Donald Trump and his presidency
New Auto-Interp
Negative Logits
.mixin
-0.16
ذ
-0.15
εÏģι
-0.15
æī¶
-0.14
conc
-0.14
okes
-0.14
rase
-0.14
ØŃاÙĦ
-0.14
Conc
-0.14
боÑĢ
-0.14
POSITIVE LOGITS
YS
0.15
satur
0.15
finity
0.14
ultz
0.14
amic
0.14
Verfüg
0.13
èĮĤ
0.13
zemÄĽ
0.13
ifting
0.13
.Base
0.13
Activations Density 0.041%