INDEX

Explanations

end of, continued, below, to be

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

 kwanza

-1.32

 siku

-1.24

↵↵

-1.21

sə

-1.20

;;

-1.18

mcu

-1.16

 produzir

-1.16

plash

-1.15

iit

-1.15

事情

-1.14

POSITIVE LOGITS

 cómo

1.63

嫆

1.49

:"

1.41

重要な

1.41

 Они

1.39

 anjo

1.36

 который

1.35

 maravilhoso

1.34

</h3>

1.33

 ellos

1.33

Activations Density 0.010%