INDEX

Explanations

Brendan

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

ⓧ

-0.69

parsedMessage

-0.51

HomeAsUpEnabled

-0.47

kuuta

-0.47

aarrggbb

-0.46

 correctes

-0.46

 CONTEST

-0.45

 kuni

-0.44

Recognizer

-0.43

 Ciel

-0.43

POSITIVE LOGITS

AndEndTag

0.57

ioutil

0.54

 урна

0.53

IntoConstraints

0.52

AndroidJUnit

0.52

 court

0.50

lwjgl

0.50

0.49

 ими

0.49

 lane

0.49

Activations Density 0.029%