INDEX

Explanations

@ followed by metadata

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

in

-1.45

-1.41

at

-1.37

-1.30

any

-1.30

 with

-1.22

one

-1.19

 every

-1.13

all

-1.12

 just

-1.11

POSITIVE LOGITS

↵↵↵↵↵↵↵↵↵↵↵↵↵

1.38

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.34

了两

1.29

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.27

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.27

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.26

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.26

噘

1.25

↵↵↵↵↵↵↵↵↵↵↵↵

1.25

了些

1.24

Activations Density 0.079%