INDEX
Explanations
quoted speech or dialogue
preceding quotations or speech
reporting speech or explanation
New Auto-Interp
Negative Logits
فريبيس
-0.65
tutte
-0.62
betweenstory
-0.60
kháu
-0.60
StructEnd
-0.58
yourselves
-0.58
تانيه
-0.57
IsContent
-0.56
segreto
-0.55
tuyo
-0.55
POSITIVE LOGITS
)"),
0.87
++]=
0.86
")));
0.85
})`
0.84
endphp
0.82
))));
0.81
)");
0.78
">',
0.77
'}),
0.76
))),
0.75
Activations Density 0.109%