INDEX

Explanations

corresponds to

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

 anadolu

-1.38

 abiye

-1.33

回到了

-1.33

 marte

-1.29

 kalem

-1.28

 champignons

-1.28

 precisamente

-1.27

 geene

-1.26

 etek

-1.25

 tekno

-1.25

POSITIVE LOGITS

 your

2.86

you

1.91

if

1.91

 with

1.56

 this

1.48

 whichever

1.47

the

1.46

 each

1.45

 that

1.41

 those

1.41

Activations Density 0.102%