INDEX

Explanations

technical documentation

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

MessageTagHelper

-0.98

脚注の使い方

-0.95

+#+#

-0.85

SourceChecksum

-0.82

WriteBarrier

-0.80

ArrowToggle

-0.77

parsedMessage

-0.77

AccessorTable

-0.77

awtextra

-0.76

WriteTagHelper

-0.76

POSITIVE LOGITS

 commerciali

0.54

 oben

0.43

 storici

0.43

 amé

0.42

 Fonten

0.42

原标题

0.40

its

0.40

 geschiedenis

0.39

 egyes

0.39

utu

0.39

Activations Density 0.091%