INDEX
Explanations
quotes or dialogue in the text
New Auto-Interp
Negative Logits
]');
-1.06
'));
-0.98
}');
-0.96
...');
-0.91
/');
-0.89
%");
-0.89
\\
-0.88
)');
-0.88
'){
-0.86
'],
-0.86
POSITIVE LOGITS
“
1.61
"
1.52
“
1.34
("1.34
"
1.31
'
1.14
="
1.14
，“
1.10
=="
1.10
”
1.09
Activations Density 0.312%