INDEX

Explanations

lists of various topics

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

ఝ

-1.45

quite

-1.40



-1.34

自体は

-1.31

 ทำ

-1.29

在我们

-1.28

 aujourd

-1.27

はこんな感じ

-1.26

っていましたが

-1.25

雱

-1.25

POSITIVE LOGITS

 numerous

1.62

 various

1.59

any

1.51

 other

1.48

 some

1.45

 countless

1.44

其他

1.42

 continual

1.40

などなど

1.38

 dozens

1.36

Activations Density 0.226%