INDEX
Explanations
full followed by descriptors
New Auto-Interp
Negative Logits
FullName
0.66
full
0.65
Full
0.64
Fullscreen
0.63
Full
0.61
đầy
0.58
FullScreen
0.55
FULL
0.54
penuh
0.52
fullscreen
0.51
POSITIVE LOGITS
fledged
1.13
fled
1.11
blown
0.98
blown
0.89
ständig
0.81
extent
0.71
াঙ্গ
0.68
bodied
0.67
throttle
0.65
ständ
0.63
Activations Density 0.049%