INDEX

Explanations

URLs and numbers

The neuron responds to numeric tokens (sequences of digits) in the text.

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

();

-1.37

eczki

-1.34

likace

-1.27

 cumplido

-1.27

 Dingen

-1.27

 ovat

-1.26

ついて

-1.24

世帯

-1.21

QUÉ

-1.21

Démographie

-1.19

POSITIVE LOGITS

by

1.59

 nineteen

1.41

 eighteen

1.38

1.30

 još

1.26

 seventeen

1.24

 sprawd

1.22

もはや

1.22

so

1.21

 then

1.20

Activations Density 0.003%