INDEX
Explanations
mentions of software updates and package management details
Chinese and Japanese characters
end of sentence punctuation
New Auto-Interp
Negative Logits
»)
-0.73
/')
-0.68
"):
-0.66
?')
-0.65
?>/
-0.63
"")
-0.59
'):
-0.59
_)
-0.56
")]
-0.56
'')
-0.56
POSITIVE LOGITS
,
1.66
。
1.64
;
1.04
。《
0.97
,
0.96
。
0.96
。「
0.95
。(
0.94
,“
0.93
。(
0.92
Activations Density 0.024%