INDEX

Explanations

the word "innocent" followed by a noun describing a person

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

 tendance

-0.75

 tendenza

-0.68

 oração

-0.64

 useRouter

-0.64

 reducers

-0.63

 τά

-0.63

 casket

-0.60

 reda

-0.58

 Kear

-0.57

 quæ

-0.57

POSITIVE LOGITS

 Innocence

1.48

innoc

1.40

Innoc

1.38

innocent

1.36

 Innoc

1.32

 Innocent

1.32

 innocent

1.29

 innocence

1.24

 inocente

1.13

 innoc

1.13

Activations Density 0.005%