INDEX
Explanations
instances of theatrical performances and productions
New Auto-Interp
Negative Logits
ediator
-0.16
ett
-0.15
kop
-0.15
_deinit
-0.14
çĶļ
-0.14
hom
-0.14
awakeFromNib
-0.14
hausen
-0.14
zes
-0.14
ä½į
-0.14
POSITIVE LOGITS
Ars
0.19
Goodman
0.18
Guth
0.18
Goods
0.17
Signature
0.17
evid
0.16
EST
0.16
Signature
0.16
Ensemble
0.16
Actors
0.16
Activations Density 0.015%