INDEX

Explanations

references or mentions of cooking activities

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

 Cook

-0.90

Cook

-0.65

urlopen

-0.53

 trust

-0.46

#![

-0.46

 libri

-0.45

 Lauter

-0.45

Tim

-0.44

وار

-0.44

ży

-0.44

POSITIVE LOGITS

 cooking

2.25

cooking

1.95

 Cooking

1.92

Cooking

1.76

elemField

1.02

featureID

1.02

rungsseite

0.91

ValueStyle

0.91

Tikang

0.88

 mergeFrom

0.86

Activations Density 0.001%