INDEX

Explanations

code and special characters

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

\xc

-0.30

_)č↵

-0.28

?).

-0.27

{//

-0.26

.")č↵

-0.25

{i

-0.24

__).

-0.24

.",č↵

-0.23

)?.

-0.23

&nbsp

-0.23

POSITIVE LOGITS

↵↵↵↵↵↵↵↵

0.28

 |↵

0.26

å¾Ģä¸ĭ

0.26

↵

0.25

*[

0.24

--

0.24

↵↵↵↵↵↵↵↵↵↵

0.24

âĹĪ

0.24

 //------------------------------------------------

0.24

Activations Density 0.275%