INDEX

Explanations

size, nature, properties

The neuron is triggered by mentions of an object’s physical size (especially words like “size,” “small,” or “miniature”).

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

as

-2.16

by

-1.57

 about

-1.48

 those

-1.43

četně

-1.42

all

-1.41

 through

-1.38

вот

-1.38

 from

-1.33

危害

-1.33

POSITIVE LOGITS

its

1.66

Its

1.57

 sois

1.45

 poderá

1.38

 lack

1.34

确实是

1.33

 poderia

1.32

 каждой

1.29

实在是

1.28

 первого

1.27

Activations Density 0.165%