INDEX

Explanations

various types and kinds

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

	RTLR

-0.27

.nt

-0.25

iben

-0.25

íĮ°

-0.23

hek

-0.22

numerusform

-0.22

ìĸķ

-0.22

steder

-0.22

@update

-0.21

.lu

-0.21

POSITIVE LOGITS

ç§įç±»

0.38

ä¸įåĲĮçļĦ

0.34

different

0.34

åĵģç§į

0.34

 different

0.33

 ÑĢÐ°Ð·Ð½ÑĭÑħ

0.33

 kinds

0.31

ä¸įåĲĮ

0.29

 types

0.28

mix

0.28

Activations Density 0.127%