INDEX
Negative Logits
chod
0.52
waterslide
0.50
rologist
0.47
herbs
0.46
charging
0.45
𝗵
0.44
rowing
0.44
मित्व
0.44
singer
0.44
rower
0.43
POSITIVE LOGITS
essay
1.18
Essays
1.14
Essay
1.13
Essay
1.13
essays
1.11
essay
0.96
निबंध
0.74
论文
0.70
dissertation
0.69
thesis
0.68
Activations Density 0.053%