INDEX

Explanations

proper names and titles

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

1.18

博士

1.01

0.97

eds

0.93

 nació

0.93

 Cities

0.93

PhD

0.92

Law

0.92

 née

0.92

于

0.92

POSITIVE LOGITS

examtype

1.36

<unused298>

1.27

ParameterActive

1.21

FAST

1.20

reactivex

1.18

idenav

1.18

trending

1.17

<unused681>

1.15

embeddings

1.15

Uppercase

1.14

Activations Density 0.257%