INDEX
Explanations
names ending in er, son, ey
New Auto-Interp
Negative Logits
relative
0.59
leap
0.58
surjective
0.57
dropdown
0.57
か
0.56
Relative
0.55
Pandas
0.54
accuracy
0.54
gulp
0.54
Echo
0.54
POSITIVE LOGITS
iller
1.05
iggins
1.02
issner
0.98
Miller
0.98
Anderson
0.97
Davis
0.95
atterson
0.93
asley
0.91
unningham
0.91
asey
0.90
Activations Density 0.028%