INDEX
Explanations
words related to pit bulls
references to pit bulls
New Auto-Interp
Negative Logits
IGH
-0.79
ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
-0.67
Idle
-0.65
dress
-0.64
Carbuncle
-0.63
lihood
-0.62
Feinstein
-0.62
soever
-0.61
issance
-0.61
Strait
-0.61
POSITIVE LOGITS
iful
1.24
cair
1.14
ifully
1.14
iless
1.13
cher
1.00
adium
0.90
Osw
0.88
oco
0.88
pits
0.81
ernal
0.81
Activations Density 0.019%