INDEX

Explanations

supplementary information or resources

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

ám

-0.90

 Internal

-0.90

diamonds

-0.85

 viszont

-0.85

TWA

-0.81

 geho

-0.80

 engl

-0.77

鸩

-0.77

 pracovní

-0.77

 собака

-0.77

POSITIVE LOGITS

Supp

1.04

 supp

0.99

مم

0.94

 wearer

0.94

supp

0.91

 specifically

0.91

料金

0.91

MENTS

0.90

arily

0.89

arev

0.89

Activations Density 0.025%