INDEX

Explanations

Code/comments, names, or start of phrases

The neuron strongly activates on the single-letter indefinite article “a.”

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

-1.51

forKey

-1.47

 wieder

-1.43

鹩

-1.41

酲

-1.38

 corsa

-1.36

and

-1.36

-1.31

POSITIVE LOGITS

 budú

1.55

avía

1.54

 normalerweise

1.53

 jadwal

1.52

 proveniente

1.52

豪華

1.52

 originalmente

1.50

wasn

1.48

ができます

1.47

 крайне

1.46

Activations Density 0.000%