INDEX

Explanations

references to news broadcasts and related media content

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

Хьажоргаш

-0.79

 news

-0.73

__':

-0.72

__':

-0.69

duled

-0.65

الحياه

-0.60

 announcement

-0.60

ilane

-0.58

 PublicKey

-0.56

 mengumumkan

-0.56

POSITIVE LOGITS

 News

1.88

News

1.46

 NEWS

0.84

 Nouvelles

0.63

 Noticias

0.58

NEWS

0.57

 Notícias

0.57

MemoryWarning

0.57

ifik

0.55

ък

0.55

Activations Density 0.005%