INDEX
Negative Logits
intersection
-0.07
uong
-0.07
ug
-0.07
ine
-0.07
Newport
-0.07
ovanie
-0.07
cud
-0.07
strstr
-0.07
uren
-0.07
Anonymous
-0.07
POSITIVE LOGITS
spaced
0.18
spacing
0.14
spacing
0.13
-spacing
0.13
_spacing
0.13
Spacing
0.12
ritmo
0.12
stagger
0.12
sequential
0.11
paced
0.11
Activations Density 0.025%