INDEX
Explanations
discussions and references related to storytelling, narratives, and shared experiences
New Auto-Interp
Negative Logits
اگ
-0.15
uze
-0.14
nj
-0.14
esiz
-0.14
usk
-0.14
.synthetic
-0.14
anik
-0.13
reopen
-0.13
es
-0.13
writer
-0.13
POSITIVE LOGITS
apol
0.18
ald
0.18
alom
0.15
lok
0.15
berger
0.14
acomp
0.14
Brain
0.14
çīĮ
0.13
164
0.13
fractional
0.13
Activations Density 0.074%