INDEX

Explanations

legal and technical terms

The neuron fires on words that serve as the main topic or title of an entry—e.g. the first or “headline” term naming a subject.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

of

-2.23

-1.70

 dakota

-1.35

-1.30

-1.29

 ktorí

-1.29

 that

-1.29

-1.23

to

-1.19

end

-1.16

POSITIVE LOGITS

 lainnya

1.46

 otras

1.46

中です

1.45

 salón

1.38

 emocion

1.34

≦)

1.34

谙

1.33

 тут

1.32

[]{"

1.32

できました

1.31

Activations Density 0.104%