INDEX

Explanations

content types

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

}}(\

-0.82

贞

-0.80

 tang

-0.77

 waterproof

-0.77

tf

-0.75

 tanto

-0.74

ProgressHUD

-0.74

listFiles

-0.74

 useCallback

-0.74

Kem

-0.73

POSITIVE LOGITS

 content

0.94

 structure

0.91

personas

0.80

navig

0.79

目次

0.76

ucap

0.76

ペラ

0.75

 PERSONS

0.75

 Estimating

0.75

 site

0.73

Activations Density 0.039%