INDEX

Explanations

verbs and actions in multiple languages

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

 görüntüleri

-2.61

᠁

-2.38

-2.36

-2.34

谖

-2.31

-2.30

 intoxicating

-2.28

-2.27

却又

-2.23

却不

-2.23

POSITIVE LOGITS

);

2.11

 gleichen

2.09

亠

2.08

 男孩

2.05

UCIÓN

2.03

It

2.00

arão

1.92

1.88

 séance

1.87

*}[

1.86

Activations Density 0.001%