INDEX
Explanations
the word "Baba" or similar variations
references to "Bab" in various contexts
New Auto-Interp
Negative Logits
SPONSORED
-0.74
IELD
-0.71
ICES
-0.71
PORT
-0.71
OPLE
-0.68
VICE
-0.67
backer
-0.67
FTWARE
-0.67
CLASSIFIED
-0.67
ABLE
-0.67
POSITIVE LOGITS
alon
0.99
Bab
0.99
oru
0.96
ulin
0.94
ule
0.91
oard
0.89
ules
0.88
onis
0.87
ula
0.86
raham
0.86
Activations Density 0.009%