INDEX

Explanations

Names and data

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

 familières

-0.56

Cot

-0.44

BUN

-0.44

 canopy

-0.41

Bun

-0.41

CopyWith

-0.40

 ponytail

-0.39

 головой

-0.39

BUN

-0.39

 Robin

-0.38

POSITIVE LOGITS

aarrggbb

0.85

 autorytatywna

0.80

 kaynağından

0.73

참고

0.71

 createSlice

0.68

phosa

0.67

 الحره

0.66

جوايز

0.66

 MainAxisSize

0.66

Activations Density 0.033%