INDEX
Explanations
references to home furnishings and their qualities
New Auto-Interp
Negative Logits
Dyn
-0.16
DOI
-0.16
Duo
-0.15
Ded
-0.15
wdx
-0.15
Disk
-0.14
Donna
-0.14
Democr
-0.14
Dynasty
-0.14
Discipline
-0.14
POSITIVE LOGITS
d
1.67
.d
0.88
д
0.84
(d
0.82
$d
0.81
d
0.81
)d
0.78
<d
0.77
*d
0.72
>d
0.71
Activations Density 0.653%