INDEX

Explanations

automatic UI elements

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

臵

-1.32

фии

-1.23

 nationales

-1.22

ΩΝ

-1.20

Métodos

-1.18

 camisas

-1.16

嵯

-1.15

🈶

-1.14

 afirmou

-1.11

 Rosé

-1.11

POSITIVE LOGITS

so

1.43

1.27

1.20

 zależ

1.16

1.14

这般

1.11

 estadounidenses

1.10

 файлы

1.06

 geprü

1.05

 przecież

1.01

Activations Density 0.095%