INDEX

Explanations

code or technical logs

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

<bos>

-1.16

 while

-1.13

 using

-1.13

 Seems

-1.13

 where

-1.13

at

-1.13

宝物

-1.10

ｼ

-1.10

 innumerable

-1.10

 Getting

-1.04

POSITIVE LOGITS

...>

1.51

 fantastic

1.41

的眼神

1.23

ことに

1.22

 VERY

1.21

.>

1.20

 estándares

1.20

*>

1.20

ඍ

1.19

#>

1.16

Activations Density 0.064%