INDEX

Explanations

the word 'ingredient' or its plural form

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

 Pavia

-0.91

 userList

-0.87

(".");

-0.85

 Domes

-0.83

inguez

-0.82

 tartalomajánló

-0.82

*>

-0.81

WriteBarrier

-0.81

mavi

-0.81

nocześnie

-0.81

POSITIVE LOGITS

 ingredients

1.61

 Ingredients

1.53

 Ingredient

1.52

 ingredient

1.45

Ingredients

1.43

ingredient

1.32

 INGREDIENTS

1.32

Ingredient

1.30

ingredients

1.28

 ingredi

1.23

Activations Density 0.002%