INDEX
Negative Logits
racist
0.39
Flick
0.38
stal
0.38
optera
0.37
acruz
0.36
WL
0.36
</tbody>
0.35
Cog
0.35
BP
0.35
tok
0.35
POSITIVE LOGITS
padding
1.77
padded
1.70
cushioning
1.63
cushioned
1.63
foam
1.59
Padding
1.58
cushions
1.56
cushion
1.55
Cushion
1.45
Foam
1.44
Activations Density 0.026%