INDEX
Explanations
phrases or concepts related to legends, particularly in storytelling or cultural references
New Auto-Interp
Negative Logits
erman
-0.18
age
-0.17
er
-0.17
erus
-0.17
erot
-0.16
bage
-0.16
era
-0.16
wares
-0.15
alars
-0.15
Creed
-0.15
POSITIVE LOGITS
äre
0.17
ry
0.17
IONS
0.16
456
0.16
ulfilled
0.16
ácil
0.15
rier
0.15
ional
0.14
ural
0.14
/current
0.14
Activations Density 0.032%