INDEX

Explanations

news article links

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

 sareng

1.59

 paredes

1.53

 następnie

1.49

 entonces

1.46

 terapia

1.38

 armazenamento

1.37

 cuadrado

1.37

 wtedy

1.36

 légumes

1.35

ร้อม

1.35

POSITIVE LOGITS

 unduly

1.42

-‘

1.36

’-

1.34

 unworthy

1.27

-,

1.25

--’

1.23

 grossly

1.22

°-

1.21

 reconsider

1.17

 extraneous

1.17

Activations Density 0.000%