INDEX
Explanations
telling stories
the start of a model-generated story, including model-turn markers, title headers, and opening narrative tokens that signal a story is beginning.
New Auto-Interp
Negative Logits
mape
0.38
ASAP
0.36
FAQ
0.36
dvs
0.36
實際
0.35
информация
0.34
資訊
0.34
FYI
0.33
informa
0.33
triage
0.33
POSITIVE LOGITS
Geschichten
0.39
erzählen
0.38
कहान
0.36
racconto
0.35
داستان
0.35
物語
0.35
कहानी
0.34
romanzo
0.34
കഥ
0.34
stories
0.33
Activations Density 0.111%