INDEX
Explanations
segments of text from scientific/religious documents with specific terminology and formatting
New Auto-Interp
Negative Logits
IEWS
-0.52
Seeder
-0.51
toy
-0.50
nonatomic
-0.49
OnInit
-0.49
şil
-0.47
toys
-0.46
toy
-0.45
nsito
-0.45
ویکیپدی
-0.45
POSITIVE LOGITS
autorytatywna
0.69
forChild
0.69
thora
0.65
كومونز
0.60
onStop
0.58
prits
0.54
FontWeight
0.52
FileDialog
0.52
setuptools
0.51
StackNavigator
0.51
Activations Density 0.120%