INDEX

Explanations

shine and its variations, glossy, paint

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

 revenues

-0.73

ReferenceEquals

-0.70

Ѿ

-0.68

 Му

-0.68

 station

-0.66

low

-0.66

꽂

-0.65

راتيج

-0.65

 Richter

-0.64

 Wonderful

-0.64

POSITIVE LOGITS

 shine

4.66

 shiny

4.09

 shining

3.75

shiny

3.47

 shines

3.44

shine

3.39

 Shine

3.39

 Shiny

3.31

 shin

3.27

Shine

3.25

Activations Density 0.053%