INDEX

Explanations

legal codes and regulations

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

 what

-1.39

and

-1.27

 this

-1.27

 even

-1.27

who

-1.23

ところに

-1.15

 crafted

-1.13

After

-1.09

 that

-1.07

だね

-1.04

POSITIVE LOGITS

<bos>

1.35

 gier

1.20

などが

1.17

Buna

1.11

がありますが

1.09

 trente

1.05

 Sekret

1.05

があります

1.05

 WHOLE

1.05

 schilder

1.04

Activations Density 0.013%