INDEX

Explanations

function parameters: types and errors

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

۔

-1.09

ıyors

-1.05

 latter

-0.96

 みた

-0.92

 ciepła

-0.92

 powiet

-0.92

푆

-0.90

 小学

-0.89

Referencia

-0.88

}}]{

-0.86

POSITIVE LOGITS

[]

1.20

but

1.16

int

1.11

www

1.10

in

1.10

 [][]

1.05

 string

1.05

``

1.03

 […]

1.02

1.00

Activations Density 0.035%