INDEX
Explanations
key moments of character development and relationship dynamics within narratives
New Auto-Interp
Negative Logits
ess
-0.16
(s
-0.15
es
-0.14
[s
-0.14
,
-0.14
uality
-0.14
ged
-0.14
oy
-0.14
EMBER
-0.13
ga
-0.13
POSITIVE LOGITS
/generated
0.17
zyst
0.16
icer
0.15
aleigh
0.15
erdale
0.15
adel
0.14
ène
0.14
orne
0.14
ofil
0.13
avia
0.13
Activations Density 1.609%