INDEX

Explanations

questions starting with Q

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

他说

-1.35

zości

-1.33

our

-1.32

֪

-1.26

𝐉

-1.26

"}";

-1.20

Isn

-1.20

 ours

-1.19

чны

-1.19

📼

-1.16

POSITIVE LOGITS

for

1.36

❗️

1.34

 would

1.32

 vicente

1.25

твра

1.24

but

1.20

 lorenzo

1.18

Roi

1.17

?'

1.17

 there

1.16

Activations Density 0.019%