INDEX

Explanations

note

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 notes

-1.43

 Note

-1.34

 Notes

-1.30

 note

-1.26

Note

-1.24

Notes

-1.19

notes

-1.17

 NOTES

-1.16

NOTES

-1.13

note

-1.09

POSITIVE LOGITS

 quæ

0.94

principalColumn

0.91

saraba

0.90

 myſelf

0.90

 raiſ

0.86

 purpoſe

0.86

 auffi

0.85

 Monfieur

0.85

 ReactDOM

0.84

 himſelf

0.82

Activations Density 0.071%