INDEX

Explanations

places lived and moved to

This neuron activates on common biographical life-event verbs (e.g. born, moved, lived, attended).

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

 występu

-1.21

ῃ

-1.08

 Vermögen

-1.07

 already

-1.02

 Objekt

-1.00

类型

-0.99

calciatore

-0.97

 Fußballspieler

-0.96

one

-0.95

POSITIVE LOGITS

of

1.27

and

1.26

ὴν

1.24

ꪔ

1.15

來

1.13

取决

1.13

這邊

1.09

⤴

1.08

 $\&$

1.07

፫

1.07

Activations Density 0.008%