INDEX
Explanations
phrases related to political debates and election details
New Auto-Interp
Negative Logits
ุà¸ģ
-0.16
ähr
-0.15
rior
-0.14
DSP
-0.14
PLL
-0.14
undermin
-0.14
fol
-0.14
-opacity
-0.14
.scalablytyped
-0.13
ãĥ¡ãĥ©
-0.13
POSITIVE LOGITS
debate
0.41
debates
0.39
Debate
0.37
deb
0.33
debating
0.31
Deb
0.29
debated
0.28
deb
0.25
.deb
0.22
moderator
0.19
Activations Density 0.070%