INDEX

Explanations

references to traditional recipes or cooking instructions

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

Burn

-0.56

hahn

-0.53

geslacht

-0.53

oredCriteria

-0.52

 Cook

-0.52

ecore

-0.49

 BURN

-0.48

 ErrIntOverflow

-0.48

 Term

-0.47

 Telex

-0.46

POSITIVE LOGITS

 recipe

2.92

 recipes

2.34

recipe

2.25

 Recipe

2.25

Recipe

2.08

 Recipes

1.86

 RECIPE

1.85

recipes

1.70

 receta

1.66

Recipes

1.63

Activations Density 0.001%