INDEX

Explanations

numbers near punctuation

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

とても

-1.63

 ladrillo

-1.52

 článek

-1.45

 pomoci

-1.43

 mármol

-1.41

 новом

-1.41

そして

-1.38

 sizzling

-1.36

 récord

-1.35

「

-1.27

POSITIVE LOGITS

</i>

1.91

 urusan

1.55

to

1.50

 from

1.49

 gdyż

1.45

̒

1.41

냄

1.38

͑

1.38

龶

1.33

panes

1.32

Activations Density 0.001%