INDEX
Explanations
mentions of conferences
references to conferences
the word "conference."
New Auto-Interp
Negative Logits
gettable
-0.71
destro
-0.68
aft
-0.66
cher
-0.65
chers
-0.64
bole
-0.63
cedented
-0.63
latent
-0.63
laus
-0.62
kowski
-0.62
POSITIVE LOGITS
conference
0.96
conferences
0.93
Conference
0.82
eers
0.81
meetings
0.81
ivals
0.81
attendees
0.79
ference
0.78
Finals
0.76
posium
0.74
Activations Density 0.017%