INDEX

Explanations

import code structure

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

罍

-1.50

 "}";

-1.48

 sech

-1.41

และ

-1.38

+;

-1.36

°;

-1.34

 vode

-1.33

 herre

-1.32

 võib

-1.29

蓴

-1.28

POSITIVE LOGITS

or

1.81

 However

1.81

 Other

1.68

see

1.60

 другими

1.50

 españolas

1.49

眶

1.48

 ONLY

1.48

 otros

1.44

来的

1.44

Activations Density 0.130%