INDEX

Explanations

code commit diff metadata

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

and

-2.23

it

-1.98

to

-1.70

-1.41

 discorso

-1.37

or

-1.34

<h2>

-1.25

-1.24

 which

-1.24

be

-1.23

POSITIVE LOGITS

 provenant

1.63

︐

1.51

 représentant

1.47

︲

1.44

 مشتری

1.38

۸

1.35

 appartenant

1.34

waitKey

1.34

learned

1.34

۹

1.33

Activations Density 0.012%