INDEX
Explanations
articles and references to professions or identities
New Auto-Interp
Negative Logits
ulp
-0.17
ieten
-0.17
irty
-0.16
arias
-0.15
abbo
-0.15
este
-0.15
esta
-0.15
olean
-0.15
nze
-0.15
aires
-0.14
POSITIVE LOGITS
ìĽIJìĿ´
0.14
vel
0.13
neutr
0.13
cube
0.13
mos
0.13
åĵ¡
0.13
.k
0.13
Mir
0.13
Sey
0.13
mf
0.12
Activations Density 0.052%