INDEX

Explanations

versions, model numbers

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

</strong>

-1.91

 Their

-1.82

-1.81

-1.77

</h2>

-1.71

 hieß

-1.66

).

-1.55

 comprised

-1.55

 They

-1.54

 were

-1.51

POSITIVE LOGITS

to

1.76

魠

1.69

href

1.63

ೣ

1.57

着脸

1.55

糴

1.52

phus

1.51

 كه

1.47

vidla

1.47

一些

1.46

Activations Density 0.115%