INDEX

Explanations

in the world and earth

This neuron detects emphatic question phrases that include a wh-word plus a location/intensifier (e.g. “how in the world,” “what on earth,” “why in the name of all things holy”).

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

ire

-1.30

 ベン

-1.23

 exas

-1.20

 rile

-1.16

 yanı

-1.15

 لأنه

-1.13

 綺麗

-1.13

up

-1.12

ємо

-1.10

 其他

-1.10

POSITIVE LOGITS

standing

1.52

 textu

1.40

mainAxisSize

1.39

 karier

1.38

телем

1.38

adamia

1.38

geſ

1.38

 pesar

1.37

)$.

1.36

 historia

1.36

Activations Density 0.015%