INDEX
Explanations
terms related to various forms of entertainment and sports, particularly those involving competition and performance
New Auto-Interp
Negative Logits
(s
-0.18
(es
-0.15
Acting
-0.15
Female
-0.15
624
-0.15
大ä¼ļ
-0.14
Stuff
-0.14
licher
-0.14
iever
-0.14
McCart
-0.14
POSITIVE LOGITS
star
0.19
veterans
0.17
icon
0.17
dynam
0.17
innov
0.17
phen
0.16
sensation
0.15
ìĬ¤íĥĢ
0.15
ppe
0.15
exponent
0.15
Activations Density 0.175%