INDEX

Explanations

selecting options or items

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

certain

-1.10

Certain

-0.96

 fhew

-0.96

 рассматри

-0.92

场比赛

-0.88

 erstmal

-0.85

nch

-0.85

链

-0.85

mathrm

-0.85

 卡片

-0.82

POSITIVE LOGITS

one

2.41

ONE

1.53

 appropriate

1.34

 which

1.31

 only

1.28

ONE

1.20

One

1.13

 один

1.13

 option

1.10

 best

1.08

Activations Density 0.023%