INDEX

Explanations

; followed by numbers

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

the

-2.02

 would

-1.59

🢒

-1.48

 There

-1.47

 first

-1.43

and

-1.43

 Even

-1.40

 habilitar

-1.40

 there

-1.39

 renovar

-1.39

POSITIVE LOGITS

んでる

1.37

 magnific

1.34

¨

1.33

 besto

1.32

他的

1.32

刚好

1.28

 insign

1.25

囮

1.25

 elektrik

1.25

小さ

1.24

Activations Density 0.041%