INDEX

Explanations

events on specific dates

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

 those

-1.33

直到

-1.16

<bos>

-1.13

and

-1.11

 then

-1.10

 protože

-1.09

 другие

-1.05

そして

-1.05

 which

-1.02

</h3>

-1.00

POSITIVE LOGITS

in

2.11

on

1.56

時間の

1.22

ironically

1.17

 дола

1.13

ДД

1.10

 alongside

1.06

escaping

1.05

 europeos

1.05

 продукти

1.05

Activations Density 0.135%