INDEX

Explanations

code delimiters and symbols

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

 sorta

-1.05

事も

-0.99

んですよ

-0.95

corrhi

-0.94

 dabei

-0.94

 těchto

-0.89

あなたが

-0.89

ことが多い

-0.88

 لهذه

-0.85

 adresa

-0.83

POSITIVE LOGITS

2.16

1.44

|\

1.29

[]

1.23

$|\

1.20

$|

1.12

|-

1.11

|$

1.10

|"

1.02

|[]

1.00

Activations Density 0.003%