INDEX
Explanations
references to specific operatic or theatrical events and performances
New Auto-Interp
Negative Logits
plays
-0.18
opera
-0.16
plays
-0.14
Play
-0.14
anna
-0.14
-0.13
Legends
-0.13
ÑģоÑĤ
-0.13
enco
-0.13
__.__
-0.13
POSITIVE LOGITS
iaux
0.17
chorus
0.17
Narr
0.17
eut
0.16
imuth
0.16
Scene
0.15
Morales
0.15
Narr
0.14
ingo
0.14
Initi
0.14
Activations Density 0.038%