INDEX

Explanations

computational software versions

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

CIL

-0.75

 Nutt

-0.71

 Oakland

-0.68

大帝

-0.68

insider

-0.67

xions

-0.66

 marido

-0.66

 Combustion

-0.66

ibs

-0.66

Davis

-0.65

POSITIVE LOGITS

 Wolfram

1.24

Wol

1.02

wol

0.91

pac

0.90

pac

0.87

 Champaign

0.85

Wol

0.84

ぜ

0.84

 Mathematica

0.84

Needs

0.79

Activations Density 0.032%