INDEX

Explanations

package dependencies or requirements

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

isés

-1.66

 Meksiko

-1.64

 Spanyol

-1.57

 Kristus

-1.56

 restoran

-1.55

 kedi

-1.55



-1.51

 teka

-1.49

綃

-1.48

 pondok

-1.48

POSITIVE LOGITS

↵↵

1.94

 with

1.77

 first

1.35

1.34

</h2>

1.33

↵

1.27

hit

1.27

harmed

1.25

もあった

1.21

1.20

Activations Density 0.611%