INDEX

Explanations

the word "hero"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.94

the

-0.76

setVerticalGroup

-0.72

 champion

-0.60

 Bourgoin

-0.58

})`

-0.57

MessageOf

-0.56

 Champion

-0.56

 hero

-0.54

 Hero

-0.54

POSITIVE LOGITS

ArgsConstructor

0.72

UserScript

0.67

 ReactDOM

0.63

IntoConstraints

0.63

parsedMessage

0.62

setupUi

0.60

 resourceCulture

0.60

 GUIDE

0.60

 hâte

0.59

rostis

0.59

Activations Density 0.933%