INDEX
Explanations
mentions of the political figures Bernie Sanders and Elizabeth Warren
New Auto-Interp
Negative Logits
íĻĺ
-0.16
igers
-0.15
jal
-0.15
und
-0.15
èĪ
-0.15
.creation
-0.15
ãĥĪãĥ«
-0.14
-0.14
cartesian
-0.14
IED
-0.14
POSITIVE LOGITS
hardt
0.18
šť
0.16
Hoe
0.15
alte
0.15
abstract
0.14
man
0.14
enties
0.14
Klaus
0.14
istant
0.14
ometer
0.14
Activations Density 0.006%