INDEX

Explanations

code syntax

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

é¾ĥ

-0.29

)application

-0.28

.Butter

-0.25

æį¢åı¥è¯Ŀ

-0.25

_HERE

-0.25

éĶĴ

-0.25

@student

-0.24

.yy

-0.24

éĵĲ

-0.23

POSITIVE LOGITS

æĢ§ä»·

0.27

åĳ¸

0.26

åı¯æĥ³

0.25

={({

0.24

 BuzzFeed

0.24

ä¼ĹæīĢåĳ¨

0.24

æīĢæīĢ

0.23

='{$

0.23

 ninete

0.23

ãĥķãĤ¡ãĥ¼

0.23

Activations Density 2.210%