INDEX

Explanations

starts of phrases or sentences

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

to

-2.14

of

-1.66

by

-1.55

on

-1.48

значно

-1.27

 mendengar

-1.22

in

-1.21

use

-1.21

for

-1.20

 που

-1.20

POSITIVE LOGITS

 protože

1.83

 мужская

1.32

 acogedor

1.32

裊

1.27

 duradero

1.22

 puissante

1.21

 maravillosas

1.20

 trám

1.20

たまた

1.19

 soportes

1.19

Activations Density 0.000%