INDEX
Explanations
references to religious or cultural institutions and figures
New Auto-Interp
Negative Logits
estekak
-0.45
MemoryWarning
-0.39
Puck
-0.38
وتسجيلات
-0.37
SequentialGroup
-0.37
Etr
-0.37
transfieras
-0.36
aarrggbb
-0.36
druid
-0.36
الحياه
-0.36
POSITIVE LOGITS
Orthodox
0.79
icons
0.79
icon
0.73
Icons
0.73
Icon
0.72
Patriarch
0.69
ícones
0.65
iconos
0.63
icône
0.63
Icons
0.59
Activations Density 0.136%