INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
incent
-0.75
Materials
-0.73
Contributions
-0.72
Interface
-0.66
Scheme
-0.66
Subst
-0.65
mie
-0.65
Rece
-0.63
material
-0.60
interchange
-0.60
POSITIVE LOGITS
ocracy
0.77
ocratic
0.74
erenn
0.70
Osc
0.70
eus
0.69
osi
0.69
oliath
0.67
ensis
0.66
awi
0.65
toe
0.63
Activations Density 0.000%
No Known Activations
This feature has no known activations.