INDEX
Explanations
muffins and other baked goods
New Auto-Interp
Negative Logits
it
0.78
มัน
0.76
他
0.69
f
0.66
<0x91>
0.66
vino
0.65
,“
0.64
nama
0.63
ال
0.62
ak
0.61
POSITIVE LOGITS
muffins
1.02
waffles
0.86
-
0.85
brownies
0.82
muffin
0.80
físicas
0.80
ास
0.80
ר
0.78
но
0.77
u
0.77
Activations Density 0.002%