INDEX

Explanations

quantities and measurements

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

 Like

-1.62

 There

-1.54

for

-1.43

 around

-1.37

 made

-1.27

There

-1.25

 Generally

-1.23

 Using

-1.23

 like

-1.22

 enjoyed

-1.22

POSITIVE LOGITS

its

1.78

übung

1.45

to

1.40

 možnosti

1.30

1.27

还不错

1.26

IComponent

1.26

了我

1.23

很赞

1.21

ſu

1.20

Activations Density 0.070%