INDEX

Explanations

svg components and illustrations

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

its

-1.33

に行ってきました

-1.21

utschen

-1.18

dza

-1.13

と話

-1.12

楽しみです

-1.10

に入り

-1.09

it

-1.08

ņas

-1.08

贔

-1.07

POSITIVE LOGITS

🔹

1.45

景观

1.34

 مخطط

1.26

 such

1.20

 hjär

1.19

itação

1.18

虽然

1.18

 wonders

1.16

私は

1.16

)=>{

1.16

Activations Density 0.011%