INDEX

Explanations

placeholders like name

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

or

1.08

and

0.89

0.78

net

0.75

0.74

av

0.74

0.71

 oder

0.71

com

0.71

of

0.71

POSITIVE LOGITS

<unused407>

1.57

AppBsky

1.57

<unused697>

1.52

捌章

1.51

<unused896>

1.50

<unused1203>

1.49

 BLUENRG

1.49

ပို

1.47

𐰃

1.47

 SPINE

1.47

Activations Density 0.030%