INDEX
Explanations
references to a specific individual, likely an athlete or notable figure
New Auto-Interp
Negative Logits
IFO
-0.18
ifo
-0.17
ailles
-0.16
etten
-0.14
tti
-0.14
converter
-0.14
trace
-0.14
isclosed
-0.14
ariat
-0.14
fold
-0.14
POSITIVE LOGITS
istani
0.18
ÏĦÏİ
0.16
ino
0.15
orte
0.14
loff
0.14
æ£ļ
0.14
λη
0.14
awks
0.14
ÑĥÑģк
0.14
gil
0.14
Activations Density 0.005%