INDEX

Explanations

style attributes with css properties

The neuron strongly activates on numeric values inside inline CSS style attributes (e.g. pixel or margin values).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits



-1.32

 provocó

-1.29

 cerró

-1.28

УДК

-1.27

дость

-1.25

 wielu

-1.23

士尼

-1.22

 verschillende

-1.22

ણ

-1.21

 Ufer

-1.20

POSITIVE LOGITS

พ

1.23

 helyez

1.19

in

1.16

 државе

1.15

ม

1.13

 دخترانه

1.12

 naturali

1.11

 voltaje

1.11

्य

1.11

Activations Density 0.002%