INDEX
Explanations
the name "Ali" in various contexts
mentions of the name "Ali."
New Auto-Interp
Negative Logits
namese
-0.81
ledge
-0.80
neys
-0.78
sylvania
-0.77
lace
-0.76
ledged
-0.75
eenth
-0.75
sburgh
-0.74
darn
-0.71
HMS
-0.70
POSITIVE LOGITS
osa
0.99
orescence
0.93
ases
0.93
Ali
0.90
Ali
0.89
Jinn
0.88
Express
0.86
veyard
0.83
otti
0.81
ased
0.78
Activations Density 0.015%