INDEX

Explanations

introducing an action

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

 people

-1.79

you

-1.76

we

-1.75

 when

-1.69

 podczas

-1.54

模样

-1.49

she

-1.49

<b>

-1.48

</h1>

-1.47

诧异

-1.41

POSITIVE LOGITS

2.22

</em>

1.55

andaş

1.36

hitheatre

1.32

 любят

1.31

例えば

1.26

bagi

1.25

たとえば

1.23

责任编辑

1.21

 Achieving

1.20

Activations Density 0.097%