INDEX

Explanations

code regulations

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

ses

-0.29

ä»¬çļĦ

-0.26

åĢĳ

-0.24

ä¸»é¢ĺæķĻèĤ²

-0.24

lings

-0.24

ä»¬éĥ½

-0.23

ech

-0.23

ä»¬

-0.22

iator

-0.21

 native

-0.20

POSITIVE LOGITS

<![

0.27

èįīæ¡Ī

0.24

-approved

0.23

 completo

0.23

åĨįéĢł

0.22

èļĮ

0.22

è§Ħå®ļçļĦ

0.22

 culpa

0.22

 consort

0.21

ä¸įè¦ģåĨį

0.21

Activations Density 0.004%