INDEX

Explanations

mentions of someone's child

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

 defaultstate

-0.80

ので

-0.71

 cherchés

-0.71

schutz

-0.62

 Panic

-0.58

 Recife

-0.57

scheme

-0.57

Personendaten

-0.57

wirk

-0.56

 Whitley

-0.56

POSITIVE LOGITS

UGHTER

1.10

 Daughter

0.93

medriver

0.92

 daughters

0.90

 Daughters

0.85

 sqlSession

0.84

Daughter

0.83

chromedriver

0.77

 Tribut

0.76

SON

0.75

Activations Density 0.015%