INDEX

Explanations

titles, quotation marks, and specific phrases

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

tomie

-0.98

 experimental

-0.92

 avant

-0.92

experimental

-0.90

 artifact

-0.83

掲載

-0.83

 Experimental

-0.82

dada

-0.82

plar

-0.81

itespace

-0.81

POSITIVE LOGITS

 utilizan

0.79

팰

0.75

Existing

0.74

 autorité

0.73

を見せて

0.71

❊

0.69

viewers

0.69

">...

0.68

oyang

0.68

 תה

0.68

Activations Density 0.024%