INDEX

Explanations

students

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adpleegd

-0.66

ummings

-0.59

 Mancha

-0.58

DebuggerNonUser

-0.57

 Debugging

-0.56

 Reviewing

-0.54

 liabilities

-0.53

TintMode

-0.53

dancer

-0.53

Ded

-0.52

POSITIVE LOGITS

Datuak

0.63

<bos>

0.57

CrossRef

0.53

ImageContext

0.48

ytet

0.48

ocirc

0.47

Personendaten

0.47

Related

0.46

ędzy

0.45

 تانيه

0.45

Activations Density 0.006%