INDEX

Explanations

he

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

+#+#

-0.63

Життєпис

-0.62

basicConfig

-0.58

was

-0.56

 belongs

-0.54

########.

-0.54

الحياه

-0.52

 doesn

-0.51

cèse

-0.51

 gynhyrchwyd

-0.50

POSITIVE LOGITS

 sleeping

0.55

ater

0.52

 område

0.51

aters

0.51

 irré

0.50

 électroniques

0.50

PoE

0.50

 riconoscimento

0.50

 netting

0.50

uie

0.50

Activations Density 0.023%