INDEX

Explanations

etc., and connector words

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

歺

-1.84

 They

-1.80

骉

-1.79



-1.73

了一

-1.73

 overly

-1.71

 vastly

-1.69

They

-1.62

 Saltar

-1.59

又在

-1.56

POSITIVE LOGITS

and

2.44

to

2.20

or

2.13

 with

2.08

 until

1.84

 during

1.80

.”

1.80

 miljoen

1.72

you

1.69

 Temmuz

1.66

Activations Density 0.015%