INDEX
Explanations
elements related to narrative structure and perspective in storytelling
New Auto-Interp
Negative Logits
Reeves
-0.18
awai
-0.16
üz
-0.16
estring
-0.14
ihan
-0.14
aman
-0.14
=forms
-0.14
.LogWarning
-0.14
AMP
-0.14
ä¿Ĺ
-0.14
POSITIVE LOGITS
pch
0.15
oucher
0.15
ÅŁt
0.15
.synthetic
0.14
Scope
0.14
chn
0.14
.nih
0.13
Fo
0.13
Scope
0.13
uras
0.13
Activations Density 0.026%