INDEX

Explanations

how something is done

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

to

-1.93

邽

-1.52

Биография

-1.49

 createContext

-1.47

}$.

-1.47

鄠

-1.46

 OGSÅ

-1.45

VIOUS

-1.44

Europ

-1.43

첵

-1.39

POSITIVE LOGITS

you

2.45

it

2.17

1.89

 iniziale

1.69

 that

1.68

),

1.62

 this

1.56

 związane

1.55

 sees

1.51

and

1.50

Activations Density 0.010%