INDEX
Explanations
the word "nominal" in various contexts
New Auto-Interp
Negative Logits
dred
-0.72
GROUND
-0.70
ween
-0.68
OHN
-0.66
steen
-0.66
Sparrow
-0.65
=-=-=-=-
-0.64
Wonderland
-0.64
DW
-0.64
YE
-0.63
POSITIVE LOGITS
adic
1.14
inates
1.12
inally
1.08
nom
1.05
ose
1.02
oses
1.01
atis
1.00
inated
0.99
inal
0.97
inate
0.96
Activations Density 0.022%