INDEX
Explanations
references to other people or entities involved in various contexts
New Auto-Interp
Negative Logits
سع
-0.71
oramic
-0.66
Miy
-0.65
[]){-0.64
a
-0.61
siri
-0.61
issau
-0.61
inaw
-0.59
avax
-0.59
tting
-0.59
POSITIVE LOGITS
Others
1.37
others
1.34
Others
1.34
OTHERS
1.33
others
1.25
Lainnya
0.99
qualcuno
0.95
Folks
0.92
else
0.90
متعلقه
0.86
Activations Density 0.065%