INDEX
Explanations
occurrences related to storytelling and narratives
New Auto-Interp
Negative Logits
umann
-0.16
cast
-0.16
anter
-0.16
zilla
-0.15
casting
-0.15
atsby
-0.15
ÌĢ
-0.15
azon
-0.15
.ba
-0.15
Walton
-0.14
POSITIVE LOGITS
ORIZ
0.15
ä»ģ
0.14
ostel
0.14
SError
0.14
]|[
0.14
rick
0.14
ấu
0.14
Stone
0.13
TZ
0.13
rell
0.13
Activations Density 0.030%