INDEX

Explanations

numbers and symbols in context

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

に行った

-1.56

Ď

-1.36

やう

-1.23

our

-1.20

 веке

-1.18

 their

-1.16

に行く

-1.16

だね

-1.14

に行って

-1.12

の人は

-1.11

POSITIVE LOGITS

 servi

1.35

 conster

1.32

 aboli

1.30

が

1.27

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

1.27

aneity

1.25

 possib

1.24

ternut

1.23

ilion

1.22

 notor

1.22

Activations Density 0.075%