INDEX

Explanations

words followed by grammatical endings

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

人は

-0.96

Kepala

-0.93

들이

-0.92

들은

-0.89

 poziomie

-0.88

리가

-0.88

さんが

-0.87

ური

-0.85

เกี่ยวกับ

-0.85

における

-0.84

POSITIVE LOGITS

에게

1.69

ものに

1.63

to

1.46

에

1.41

 kepada

1.40

に

1.21

にも

1.17

の人に

1.16

さに

1.13

みに

1.09

Activations Density 0.013%