INDEX
Explanations
code components and actions
New Auto-Interp
Negative Logits
whilst
0.84
during
0.83
while
0.76
rather
0.75
أثناء
0.75
WHILE
0.73
despite
0.72
であることを
0.72
тоді
0.71
during
0.70
POSITIVE LOGITS
allows
1.55
用来
1.43
позволяет
1.41
allows
1.40
waarmee
1.40
permettant
1.33
allowing
1.31
allowing
1.31
lets
1.27
用于
1.27
Activations Density 0.274%