INDEX

Explanations

rights reserved and license

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

ése

-0.66

队员

-0.64

 finalist

-0.63

HECK

-0.62

shund

-0.62

 potenci

-0.61

ссажи

-0.60

꺾

-0.60

 coder

-0.60

 elasticity

-0.60

POSITIVE LOGITS

摩

0.72

noticias

0.69

structured

0.69

ciao

0.68

statue

0.68

免

0.66

 dicembre

0.65

 hold

0.63

ãn

0.63

 Hold

0.63

Activations Density 0.095%