INDEX

Explanations

URLs, code, questions, headers

The neuron fires on tokens composed of digits, especially sequences of numbers as appear in phone numbers or numeric codes.

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

our

-1.63

 also

-1.38

",

-1.31

we

-1.28

</th>

-1.26

-1.20

',

-1.18

 supporting

-1.16

 която

-1.13

$\%$

-1.12

POSITIVE LOGITS

توضیحات

1.59

Thema

1.54

دانلود

1.30

Abend

1.28

Transk

1.24

AllAfrica

1.23

Gratis

1.20

Kult

1.18

 rigide

1.18

 作り方

1.18

Activations Density 0.003%