INDEX

Explanations

representatives and practitioners

This neuron activates on plural nouns that denote members or examples of a category (e.g. representatives, practitioners, examples).

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

-1.59

しましたが

-1.35

つて

-1.29

しました

-1.25

ッと

-1.23

 pierwszym

-1.21

别人的

-1.20

}$

-1.19

 každého

-1.18

 akku

-1.16

POSITIVE LOGITS

 Werken

1.40

БИ

1.33

ภาพ

1.30

觏

1.27

ৄ

1.27

酲

1.27

 nowrap

1.25

 wares

1.25

ВП

1.25

When

1.23

Activations Density 0.077%