INDEX

Explanations

names of places and things

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

 polaire

-1.18

 ഒരു

-1.09

 Examin

-1.09

ほとん

-1.09

 prato

-1.08

 predominantly

-1.05

 unanim

-1.03

ﮏ

-1.02

真的

-1.02



-1.01

POSITIVE LOGITS

in

1.66

any

1.40

 what

1.38

 What

1.24

at

1.24

 after

1.22

↵

1.20

 before

1.15

by

1.11

it

1.10

Activations Density 0.048%