INDEX

Explanations

code and programming keywords

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

 повече

-1.52

 because

-1.44

 няколко

-1.39

 всички

-1.38

 различни

-1.36

 малко

-1.23

 客厅

-1.20

 говорит

-1.17

 antiguas

-1.16

 всеки

-1.14

POSITIVE LOGITS

 estime

1.35

rably

1.35

(&:

1.28

 setempat

1.27

 vérité

1.26

)}$

1.26

otropy

1.25

)$

1.25

}}.

1.23

estimated

1.23

Activations Density 0.050%