INDEX

Explanations

end of a list with "more"

This neuron detects the word “more” when it’s used to cap off a list (e.g., in phrases like “and more”).

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

and

-1.70

()?;

-1.67

 και

-1.59

-1.52

</h5>

-1.52

\\

-1.50

\&

-1.37

 focusing

-1.35

 hierdie

-1.32

Ꮭ

-1.31

POSITIVE LOGITS

</strong>

1.73

棐

1.61

 umfasst

1.58

 coloris

1.52

盅

1.48

 ihrem

1.45

回到了

1.44

 dergleichen

1.43

‌ی

1.43

The

1.43

Activations Density 0.019%