INDEX

Explanations

list items number

The neuron detects square‐bracket list markers (e.g. the “\[” used in markdown checklist or list item syntax).

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

 hırka

-2.36

饜

-2.28

*</

-2.27

 火鍋

-2.22

!';

-2.22

 calcetines

-2.20

삵

-2.19

 стоковые

-2.17

...»

-2.16

…»

-2.14

POSITIVE LOGITS

The

3.33

It

3.31

In

3.03

If

2.66

to

2.64

 There

2.63

As

2.59

At

2.50

 Since

2.44

 there

2.39

Activations Density 0.020%