INDEX

Explanations

numbers and measurements

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

نما

-1.60

Αν

-1.59

Για

-1.58

 varje

-1.51

᪥

-1.47

ys

-1.46

的一声

-1.44

 jesús

-1.42

 hermé

-1.42

</h4>

-1.41

POSITIVE LOGITS

zyści

1.52

gı

1.34

 если

1.34

出来て

1.29

時に

1.29

 lẽ

1.28

Bans

1.27

icona

1.27

the

1.26

 tratan

1.24

Activations Density 0.004%