INDEX
Explanations
the surname "Li" followed by a single character
references to the name "Li."
New Auto-Interp
Negative Logits
warp
-0.73
warped
-0.68
pagan
-0.63
Preview
-0.63
refresh
-0.62
bob
-0.62
altar
-0.61
ÙIJ
-0.60
shaping
-0.60
cones
-0.60
POSITIVE LOGITS
Li
3.98
Li
3.21
li
1.82
Zhao
1.62
Liu
1.57
LI
1.54
Wang
1.52
Zhang
1.51
Huang
1.43
LIA
1.42
Activations Density 0.014%