INDEX
Explanations
words related to physical injuries, medical conditions, and bodily fluids
New Auto-Interp
Negative Logits
irlf
-0.77
igmat
-0.70
ovie
-0.68
Franchise
-0.68
ukong
-0.68
Tale
-0.67
Mash
-0.65
Logo
-0.65
Contrast
-0.65
Ital
-0.63
POSITIVE LOGITS
flows
1.14
flows
1.09
flow
1.07
fulness
1.05
shed
0.97
bags
0.96
flow
0.93
bytes
0.93
lessness
0.92
flowing
0.91
Activations Density 3.002%