INDEX

Explanations

numbers in citations

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

くれた

-0.83

 обратно

-0.81

そんなに

-0.80

やってる

-0.75

ARS

-0.75

InputBorder

-0.74

欣赏

-0.73

風景

-0.73

alz

-0.73

 lutar

-0.73

POSITIVE LOGITS

 chapter

1.10

 chapters

0.95

 chapitre

0.91

 trinken

0.89

discussion

0.88

 heureuse

0.87

 eksklu

0.86

蒸

0.85

 trener

0.84

 dié

0.83

Activations Density 0.007%