INDEX
Negative Logits
ইন্দু
0.34
TYPE
0.32
कटोच
0.32
ډول
0.31
sampler
0.31
Calculation
0.31
mapped
0.30
Layer
0.30
iterate
0.29
features
0.29
POSITIVE LOGITS
there
0.63
there
0.53
nobody
0.51
people
0.49
we
0.49
THERE
0.48
everyone
0.47
humans
0.46
it
0.45
niemand
0.43
Activations Density 0.030%