INDEX

Explanations

programming collections

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

↵

-1.53

id

-1.26

颯

-1.25

-1.24

 find

-1.23

for

-1.23

too

-1.23

);

-1.23

 ведь

-1.23

anglicky

-1.21

POSITIVE LOGITS

ྥ

1.43

珢

1.41

 leão

1.38

絶対に

1.36

 smör

1.30

褲

1.29

 ewigen

1.28

 birra

1.27

 cappella

1.26

 this

1.23

Activations Density 0.007%