INDEX

Explanations

list markers followed by words

The neuron activates on standalone numeric tokens (integers or decimals), i.e. it detects numbers and measurements 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

two

-2.41

 took

-2.33

had

-2.27

 four

-2.25

and

-2.23

 will

-2.22

 three

-2.17

 well

-2.13

 made

-2.13

<h3>

-2.05

POSITIVE LOGITS

 ſol

2.42

 unſ

2.23

 juſ

2.22



2.16

ſy

2.06

 スリーブ

2.03

︕

2.00

馊

1.98

鮡

1.94

 SIMILAR

1.92

Activations Density 0.035%