INDEX
Explanations
references to Donald Trump and his administration's actions and statements.
New Auto-Interp
Negative Logits
=os
-0.07
慶
-0.07
Forge
-0.06
celed
-0.06
(Collider
-0.06
MET
-0.06
Helen
-0.06
�
-0.06
医院
-0.06
SDK
-0.06
POSITIVE LOGITS
Trump
0.16
Trump
0.12
trump
0.09
prom
0.07
prim
0.07
-Trump
0.07
.PNG
0.07
<Select
0.07
منط
0.07
trumpet
0.07
Activations Density 0.007%