INDEX

Explanations

numbers or symbols

The neuron is triggered by numeric values in table cells—especially decimal or floating‐point numbers.

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

鹩

-1.65

 poud

-1.56

墊

-1.55

 poft

-1.50

 ส์

-1.49

 camiset

-1.47

 ſol

-1.47

 biber

-1.45

pê

-1.44

Eſ

-1.43

POSITIVE LOGITS

is

1.35

1.33

 increase

1.27

 From

1.22

 между

1.20

 его

1.16

can

1.16

et

1.15

At

1.15

Activations Density 0.045%