INDEX

Explanations

function calls and checks

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

si

-2.69

THE

-2.61

↵↵

-2.53

 thier

-2.48

 THEIR

-2.48

 termed

-2.47

 barring

-2.42

可以

-2.42

MAN

-2.41

vi

-2.38

POSITIVE LOGITS

2.63

ᯅ

2.63

对方的

2.53

replyreport

2.48

Выводы

2.44

 abiye

2.41

ization

2.38

Другие

2.34

Недостатки

2.34

谙

2.33

Activations Density 0.003%