INDEX
Explanations
terms related to characters and their roles in a narrative
New Auto-Interp
Negative Logits
òng
-0.16
luk
-0.16
reater
-0.15
isson
-0.15
ä¼
-0.15
ackage
-0.14
Temple
-0.14
apon
-0.14
erring
-0.14
į¨
-0.14
POSITIVE LOGITS
late
0.28
Nam
0.27
late
0.24
Adj
0.22
spr
0.21
Nam
0.21
Spr
0.20
wort
0.19
spr
0.19
Late
0.19
Activations Density 0.020%