INDEX

Explanations

license and copyright notice

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

 will

-1.67

</h5>

-1.46

alış

-1.45

we

-1.38

金

-1.37

ᵕ

-1.32

 should

-1.28

We

-1.27

ことはありません

-1.26

 would

-1.25

POSITIVE LOGITS

1.98

1.96

lâ

1.52

 utilizó

1.39

 acabó

1.38

 provocó

1.36

řízen

1.27

 generó

1.25

 zależ

1.25

bê

1.25

Activations Density 0.224%