INDEX
Explanations
references to Shakespeare and theatrical productions
New Auto-Interp
Negative Logits
emey
-0.19
ÑĤоÑİ
-0.17
جÛĮ
-0.16
byss
-0.15
oire
-0.15
krat
-0.15
Telegram
-0.14
erland
-0.14
gis
-0.14
Rockefeller
-0.14
POSITIVE LOGITS
Shakespeare
0.39
Ham
0.36
akespeare
0.34
Romeo
0.30
Ham
0.29
Globe
0.29
Bard
0.28
Shake
0.28
ham
0.28
Lear
0.27
Activations Density 0.094%