INDEX

Explanations

age or duration referring to years

The neuron fires on the base noun in hyphenated quantitative modifiers (e.g. “years” in “13-year-old,” “thousands” in “tens-of-thousands,” “high” in “career-high,” “time” in “all-time”).

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

 affitto

-1.56

 bekannte

-1.50

 biß

-1.45

 arrivo

-1.44

Forgery

-1.40

Espace

-1.39

 sposob

-1.39

 großartige

-1.39

Noticia

-1.37

偸

-1.37

POSITIVE LOGITS

–

1.52

1.48

########.

1.41

›

1.41

ș

1.39

eeeeeeee

1.38

з

1.36

ಠ

1.36

1.35

»

1.34

Activations Density 0.089%