INDEX

Explanations

positive descriptive adjectives

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

えっ

-1.49

ほら

-1.41

 pries

-1.37

 oeuvres

-1.37

他已经

-1.29

 маникюр

-1.27

 certes

-1.26

 rapports

-1.26

誰でも

-1.26

 esfuer

-1.24

POSITIVE LOGITS

and

2.14

そして

1.14

This

1.12

<bos>

1.09

AND

1.07

 Armee

1.05

ESSMENT

1.03

etc

1.02

 และ

1.01

ADORES

1.01

Activations Density 0.041%