INDEX

Explanations

code snippets and punctuation

The neuron is detecting numeric tokens (individual digits or multi‐digit numbers) in code or data.

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

にほんブログ村

-1.27

生肖

-1.24

sierung

-1.23

 století

-1.20

Галерея

-1.17

-1.15

presumably

-1.14

ironically

-1.11

knew

-1.10

 mouseY

-1.10

POSITIVE LOGITS

та

1.35

 diperhatikan

1.22

 móg

1.20

These

1.16

два

1.13

待つ

1.13

these

1.11

ություն

1.10

 lenguas

1.10

Activations Density 0.124%