INDEX
Explanations
quotes or dialogue in the text
long quoted passages from books and texts.
New Auto-Interp
Negative Logits
newOwner
-0.49
uisine
-0.47
thasone
-0.45
ohnehin
-0.41
bArr
-0.41
?>/
-0.39
+#+#
-0.39
们
-0.38
ModelRenderer
-0.38
dint
-0.37
POSITIVE LOGITS
aldus
0.71
Quoted
0.60
quoted
0.59
―
0.59
quoted
0.57
surla
0.55
emphasis
0.55
Quoted
0.54
extract
0.54
terdengar
0.53
Activations Density 0.282%