INDEX
Explanations
references to theater and theatrical concepts
New Auto-Interp
Negative Logits
sonian
-0.17
uela
-0.17
воÑİ
-0.15
ivatel
-0.15
chwitz
-0.15
isle
-0.15
pec
-0.14
dán
-0.14
uli
-0.14
tab
-0.14
POSITIVE LOGITS
erv
0.17
onds
0.15
affer
0.15
usch
0.14
erview
0.14
ayment
0.14
Perkins
0.14
-document
0.13
tractive
0.13
fst
0.13
Activations Density 0.031%