INDEX
Explanations
references to theatrical or performance-related stages
New Auto-Interp
Negative Logits
iglia
-0.18
rych
-0.18
ntag
-0.17
loff
-0.17
apel
-0.16
s
-0.15
ngo
-0.15
è°±
-0.15
eness
-0.15
ssue
-0.15
POSITIVE LOGITS
coach
0.36
craft
0.25
773
0.20
Presence
0.18
Presence
0.17
ValuePair
0.16
fright
0.16
.Stage
0.16
ë³Ħ
0.15
aravel
0.15
Activations Density 0.018%