INDEX

Explanations

page numbers and dates

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

to

-1.73

 because

-1.37

for

-1.30

as

-1.22

and

-1.18

by

-1.13

 this

-1.10

 like

-1.07

 from

-1.07

 while

-1.06

POSITIVE LOGITS

 réjou

1.36

 refroid

1.34

 rembour

1.30

 manquer

1.28

 rafraî

1.27

 bross

1.23

 aras

1.20

 prét

1.19

 géant

1.17

 verrou

1.16

Activations Density 0.009%