INDEX
Explanations
references to events or topics related to conventions
repeated mentions of the term "convention."
New Auto-Interp
Negative Logits
lasses
-0.86
cam
-0.69
tera
-0.68
iless
-0.67
arma
-0.66
rodu
-0.63
obi
-0.63
ï¸ı
-0.62
lights
-0.62
wx
-0.60
POSITIVE LOGITS
eers
1.41
convention
0.95
eering
0.93
eer
0.92
ally
0.91
ality
0.91
Convention
0.89
naire
0.89
delegates
0.88
hall
0.86
Activations Density 0.030%