INDEX
Explanations
unique structural elements or symbols in text
New Auto-Interp
Negative Logits
iſt
-1.08
indígen
-1.02
iſen
-1.00
ſcher
-0.99
ſind
-0.99
queſta
-0.97
mpagne
-0.95
verſ
-0.94
ویکیپدی
-0.93
majánló
-0.93
POSITIVE LOGITS
}
2.30
}
1.48
)}
1.48
.}
1.45
}
1.41
]}
1.37
}}
1.34
"}
1.33
}}}
1.33
'}
1.30
Activations Density 0.362%