INDEX

Explanations

section headers or list items

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

these

-1.55

those

-1.40

相変わらず

-1.34

 anhänger

-1.33

こいつ

-1.31

頑張って

-1.30

 sprüche

-1.30

gruppo

-1.26

 aqueles

-1.26

他们

-1.24

POSITIVE LOGITS

1.34

 There

1.31

 What

1.29

1.27

 مواليد

1.26

If

1.25

1.24

1.23

</h2>

1.20

Activations Density 0.002%