INDEX

Explanations

constraints and limitations

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



-1.34

xii

-1.32

xvii

-1.30

 donnent

-1.30

itosti

-1.26

 keker

-1.24

yup

-1.22

mvh

-1.19

haël

-1.18

 Hinsicht

-1.16

POSITIVE LOGITS

but

1.38

クロ

1.34

and

1.32

 votación

1.31

but

1.30

else

1.28

lottesville

1.24

 terjangkau

1.22

 have

1.21

(?)

1.20

Activations Density 0.034%