INDEX
Explanations
quotes and quotations in the text
New Auto-Interp
Negative Logits
Efq
-0.98
itſelf
-0.95
Liefs
-0.94
يتيمه
-0.93
^(@)
-0.93
>\<^
-0.93
$_"
-0.92
\\
-0.91
IBRARY
-0.89
Obrigada
-0.88
POSITIVE LOGITS
“
2.38
“
2.29
‘
1.60
”
1.55
、“
1.52
,“
1.52
(“
1.51
(“
1.47
.“
1.47
=“
1.42
Activations Density 0.219%