INDEX

Explanations

component part or end

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

、

-1.62

 nuoc

-1.48

 about

-1.36

čného

-1.34

 hacían

-1.33

 egenskaper

-1.30

THEY

-1.30

ftw

-1.30

/>";

-1.30

ientras

-1.29

POSITIVE LOGITS

our

2.02

了你

1.74

</b>

1.66

！】

1.63

 longtime

1.57

徘

1.57

向了

1.52

はもう

1.48

жает

1.46

 können

1.45

Activations Density 0.023%