INDEX

Explanations

examples of specific instances

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

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.11

teness

-1.09

 différentes

-1.06

着自己的

-1.05

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.04

 lediglich

-1.04

 prêtre

-1.02

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.02

 stej

-1.02

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.01

POSITIVE LOGITS

 here

1.64

 today

1.49

 ones

1.46

 example

1.45

 this

1.31

now

1.20

 ours

1.20

 उदाहरण

1.18

 herein

1.17

 these

1.16

Activations Density 0.050%