INDEX
Explanations
mentions of a specific name, likely relating to a wrestling context
New Auto-Interp
Negative Logits
izer
-0.20
IZER
-0.18
åIJ
-0.16
esh
-0.16
ihan
-0.15
ysts
-0.15
a
-0.15
amer
-0.15
elson
-0.15
stra
-0.15
POSITIVE LOGITS
rett
0.23
oslav
0.21
thur
0.21
allax
0.19
ritos
0.19
ngo
0.18
ufe
0.17
Jar
0.17
zÄħ
0.17
ÙĪÛĮس
0.17
Activations Density 0.008%