INDEX

Explanations

note or reference

ordinary, simple, dangerous, experience

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

うち

0.47

ozems

0.47

 所以

0.47

 தொகை

0.46

 מר

0.46

amides

0.45

ಂಚ

0.44

 তবু

0.44

 लिहाजा

0.44

𝘳

0.43

POSITIVE LOGITS

لاحظ

0.50

 gezegd

0.49

 NOTE

0.45

 adresu

0.43

ิทธิ

0.42

між

0.42

주의

0.41

টিত

0.41

 riferimento

0.39

件事情

0.39

Activations Density 0.002%