INDEX

Explanations

non- followed by other words

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

or

-1.83

by

-1.77

as

-1.52

 entram

-1.33

🧐

-1.26

and

-1.24

)]

-1.22

")]

-1.21

 短发

-1.21

рована

-1.19

POSITIVE LOGITS

 outside

1.57

Escuela

1.51

也将

1.48

 étrang

1.45

concepto

1.38

 dirigez

1.38

 eşofman

1.36

 atardecer

1.35

 Deinen

1.34

 ayakkab

1.31

Activations Density 0.061%