INDEX

Explanations

color properties or values

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

ּוֹ

-1.53

ֶּ

-1.39

amaño

-1.34

reht

-1.20

 cocaína

-1.20

 horri

-1.18

 volledige

-1.18

ranslated

-1.16

chery

-1.16

の変化

-1.16

POSITIVE LOGITS

 that

1.48

</i>

1.27

 entanto

1.22

 quae

1.20

our

1.07

1.05

 ویتامین

1.02

 вернуть

1.01

 kolei

0.96

In

0.95

Activations Density 0.237%