INDEX
Explanations
phrases indicating the material something is made from
references to the materials or sources used in making items
New Auto-Interp
Negative Logits
osponsors
-0.89
heastern
-0.74
veland
-0.74
doms
-0.70
ushered
-0.69
yip
-0.68
merce
-0.68
show
-0.68
akia
-0.68
tn
-0.67
POSITIVE LOGITS
scratch
1.32
mole
0.82
ãĤ©
0.80
tissue
0.72
humble
0.71
vegetable
0.71
materials
0.70
LEGO
0.70
fiber
0.69
pure
0.69
Activations Density 0.146%