INDEX
Explanations
discourse related to political debates and their regulations
New Auto-Interp
Negative Logits
Incoming
-0.15
.ribbon
-0.14
.scalablytyped
-0.14
Incoming
-0.14
Worship
-0.14
emies
-0.14
uben
-0.13
акон
-0.13
097
-0.13
appoint
-0.13
POSITIVE LOGITS
debate
0.47
debates
0.42
Debate
0.42
moderators
0.37
debating
0.36
deb
0.36
moderator
0.34
debated
0.32
.deb
0.30
Deb
0.30
Activations Density 0.057%