INDEX
Explanations
menu options and console output
New Auto-Interp
Negative Logits
inhibited
0.44
stalled
0.44
scorched
0.41
philanthropic
0.41
_
0.41
philanthropist
0.40
$
0.40
"$
0.40
حظ
0.40
stalls
0.39
POSITIVE LOGITS
ITA
0.50
Defocused
0.46
risulta
0.46
YLE
0.44
இற
0.43
Citation
0.43
risult
0.43
Clar
0.42
আমাদের
0.41
璐
0.41
Activations Density 0.001%