INDEX
Explanations
names of individuals involved in various activities or professions
references to coaches and athletes in sports contexts
New Auto-Interp
Negative Logits
',"
-0.63
),"
-0.63
'."
-0.60
Ire
-0.60
SourceFile
-0.57
.")
-0.57
notor
-0.57
GOODMAN
-0.56
,'"
-0.56
STDOUT
-0.55
POSITIVE LOGITS
↵
1.31
↵↵
1.09
->
0.95
[/
0.93
|
0.93
<|endoftext|>
0.88
(+
0.87
(-
0.86
âĨĴ
0.86
(%)
0.85
Activations Density 0.624%