INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
.son
-0.16
ì²
-0.15
arf
-0.14
zik
-0.13
SON
-0.13
343
-0.13
yr
-0.13
ossa
-0.13
ancell
-0.13
/AFP
-0.13
POSITIVE LOGITS
looking
0.90
looking
0.86
-looking
0.78
sounding
0.72
Looking
0.72
Looking
0.69
seeming
0.45
smelling
0.39
appearing
0.39
ounding
0.38
Activations Density 0.325%