INDEX
Explanations
elements of magical realism and fantasy in narratives
New Auto-Interp
Negative Logits
sanitize
-0.16
anja
-0.16
onte
-0.15
boro
-0.15
atti
-0.14
ulton
-0.14
inski
-0.14
sam
-0.13
utra
-0.13
ellas
-0.13
POSITIVE LOGITS
è©
0.15
Blades
0.15
extrapol
0.14
Nikol
0.14
ome
0.14
har
0.14
æľŃ
0.14
ara
0.14
èĭ
0.13
rew
0.13
Activations Density 0.299%