INDEX
Explanations
mentions of the name "Donald Trump"
mentions of Donald Trump
New Auto-Interp
Negative Logits
nexus
-0.78
urgency
-0.66
guiActiveUnfocused
-0.66
interest
-0.65
glim
-0.64
Completed
-0.63
Cooldown
-0.62
aband
-0.62
essage
-0.62
reinforcement
-0.62
POSITIVE LOGITS
Trump
1.41
Donald
1.08
Trump
1.01
trump
0.97
son
0.97
Donald
0.93
realDonaldTrump
0.93
TRUMP
0.92
Glover
0.92
Judd
0.92
Activations Density 0.031%