INDEX

Explanations

code diff context and content

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

-1.41

着一个

-1.33

 raccont

-1.27

ază

-1.24

li

-1.22

-1.20

ți

-1.20

買い

-1.19

了一個

-1.19

})

-1.18

POSITIVE LOGITS

liśmy

1.52

⅗

1.46

 ਨਾਲ

1.41

⅖

1.40

 któ

1.39

 informacija

1.37

1.36

nji

1.32

łoży

1.32

 povezave

1.30

Activations Density 0.002%