INDEX
Explanations
mathematical formulas with fractions
New Auto-Interp
Negative Logits
hende
-0.77
fı
-0.76
boson
-0.75
minion
-0.75
تمر
-0.75
GHS
-0.74
fié
-0.73
Waugh
-0.73
ayam
-0.73
zir
-0.73
POSITIVE LOGITS
factorial
1.07
factorial
0.96
jabón
0.86
vello
0.86
minutes
0.82
enciaga
0.82
明月
0.80
inkai
0.80
Beteiligung
0.79
Sử
0.79
Activations Density 0.027%