INDEX

Explanations

code blocks or curly braces

The neuron fires on standalone curly‐brace tokens (i.e. the “{” or “}” that mark code‐block delimiters).

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

<em>

-2.41

氿

-2.39

<<<<<<<

-2.33

我們

-2.30

更

-2.30

Let

-2.22

isation

-2.16

Of

-2.16

 μια

-2.13

ing

-2.11

POSITIVE LOGITS

🫅

2.78

 retratos

2.58

linawan

2.55

횃

2.52

諴

2.50

 explicado

2.34

arangay

2.28

ctores

2.27

\&

2.25

 that

2.23

Activations Density 0.004%