INDEX

Explanations

for followed by specific entities

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

ଢ

-1.47

 those

-1.39

 what

-1.38

 dinosaurio

-1.34

isit

-1.34

自己的

-1.29

($__

-1.27

𖤣

-1.27



-1.27

zembro

-1.26

POSITIVE LOGITS

of

1.72

1.45

*}$

1.24

 Support

1.16

from

1.16

Co

1.13

1.12

 intimated

1.10

чного

1.10

}$.

1.10

Activations Density 0.137%