INDEX
Explanations
mentions of the name "Trump" in various contexts
New Auto-Interp
Negative Logits
Associated
-0.16
anship
-0.16
gate
-0.14
aille
-0.14
uib
-0.14
loom
-0.13
ÑĥÑī
-0.13
Associated
-0.13
-associated
-0.13
anan
-0.13
POSITIVE LOGITS
fov
0.18
467
0.14
rip
0.14
gangs
0.14
eto
0.14
bum
0.14
κή
0.14
.TestCase
0.13
ews
0.13
ÙĪØ§
0.13
Activations Density 0.022%