INDEX

Explanations

names after punctuation

The neuron spotlights standalone numeric tokens (multi‐digit numbers) 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

久し

-1.41

に於

-1.36

cterms

-1.29

様な

-1.28

 gevallen

-1.27

StoryboardSegue

-1.27

の概要

-1.27

ができます

-1.26

thodes

-1.24

ようで

-1.24

POSITIVE LOGITS

 with

1.38

1.35

1.33

1.23

1.22

が

1.20

</em>

1.16

 only

1.15

1.14

ā

1.13

Activations Density 0.003%