INDEX

Explanations

Technical documents and 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

BeginContext

-0.68

IntoConstraints

-0.62

ERTE

-0.62

enderror

-0.60

hler

-0.60

verna

-0.57

 gian

-0.57

nello

-0.56

tilus

-0.56

Cleaning

-0.56

POSITIVE LOGITS

 tropicales

0.43

 pesada

0.42

 oxígeno

0.40

ensement

0.40

lenmiş

0.39

HasIndex

0.38

 originali

0.38

 forêt

0.37

паковка

0.36

 palsy

0.36

Activations Density 0.000%