INDEX

Explanations

pet

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

<bos>

-0.55

shima

-0.45

таж

-0.45

Geografie

-0.44

 entrevist

-0.43

еро

-0.41

magitan

-0.39

 didukung

-0.39

antenna

-0.39

 Rade

-0.39

POSITIVE LOGITS

Personensuche

0.79

 незавершена

0.72

httphttps

0.68

SuspendLayout

0.65

Predecesor

0.65

postsleuth

0.64

出版年

0.63

__(/*!

0.61

 tfsi

0.61

 slowest

0.60

Activations Density 0.073%