INDEX
Explanations
references to the name "Simon."
New Auto-Interp
Negative Logits
itel
-0.20
eenth
-0.18
aney
-0.16
veled
-0.15
ourcem
-0.15
heid
-0.14
ulence
-0.14
éĻį
-0.14
(*)(
-0.14
/cli
-0.14
POSITIVE LOGITS
minded
0.18
onas
0.17
etta
0.16
-minded
0.16
енÑģ
0.16
ait
0.15
236
0.15
odelist
0.15
anch
0.15
onest
0.15
Activations Density 0.034%