INDEX
Explanations
character names and relationships in narratives
New Auto-Interp
Negative Logits
á»IJ
-0.17
cÃŃ
-0.17
iddet
-0.16
μοί
-0.15
idders
-0.15
DataTask
-0.14
tplib
-0.14
ISCO
-0.14
enge
-0.14
-thumbnails
-0.14
POSITIVE LOGITS
essler
0.15
Character
0.15
aya
0.14
“
0.14
Wid
0.14
=o
0.14
Gilbert
0.14
icht
0.14
å¹³
0.14
’s
0.13
Activations Density 0.045%