INDEX

Explanations

code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SpringRunner

-0.61

 Swit

-0.44

 createSlice

-0.41

ğunu

-0.40

unit

-0.40

UNIT

-0.40

 Dada

-0.39

orsa

-0.39

units

-0.38

 skrive

-0.38

POSITIVE LOGITS

 cherchés

0.62

 Delayed

0.62

ArrowToggle

0.61

 Learning

0.60

 kaynağından

0.57

 autorytatywna

0.57

Enllaces

0.56

 Learned

0.54

 ostavi

0.54

}?>

0.53

Activations Density 0.001%