INDEX
Explanations
mentions of the name "Cur" in a text
mentions of the name "Cur."
New Auto-Interp
Negative Logits
ãģ®éŃĶ
-0.69
é¾įå
-0.68
ographical
-0.67
ARY
-0.66
naires
-0.66
Covenant
-0.65
ILA
-0.63
guiActiveUnfocused
-0.63
EMS
-0.63
actory
-0.62
POSITIVE LOGITS
iosity
1.17
tain
1.05
ricular
1.04
few
1.04
rencies
1.03
rie
1.02
rier
0.99
acies
0.94
rences
0.94
rying
0.94
Activations Density 0.012%