INDEX

Explanations

multiple languages

This neuron activates on sequences of non-Latin (Unicode) characters, i.e. tokens in scripts like Cyrillic, Japanese, Arabic, Thai, etc.

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

 there

-1.32

ゎ

-1.31

guitarra

-1.30

 宝宝

-1.29

就是这样

-1.27

 вони

-1.25

número

-1.23

彼らは

-1.23

 бывает

-1.21

このように

-1.21

POSITIVE LOGITS

 Karakter

1.41

lised

1.38

 Baş

1.32

tened

1.30

~”

1.28

？”

1.28

向了

1.27

<>

1.27

 Teknik

1.26

…,

1.25

Activations Density 0.049%