INDEX
Explanations
terms related to drama and theatrical performances
New Auto-Interp
Negative Logits
ieg
-0.16
drafted
-0.16
iaux
-0.15
vrier
-0.15
iegel
-0.15
imeter
-0.15
ave
-0.14
draft
-0.14
drilling
-0.14
ä½µ
-0.14
POSITIVE LOGITS
mers
0.26
ming
0.25
queen
0.23
buie
0.23
atic
0.23
atur
0.23
queens
0.23
mond
0.22
íĭ±
0.21
Queen
0.21
Activations Density 0.020%