INDEX

Explanations

```bracket or matrix delimiters```

The neuron strongly activates on left square‐bracket characters (e.g. `[` or escaped `\[`), as used in regex character‐classes or TeX/math 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

していく

-1.03

 %@",

-0.91

thief

-0.83

 Auffassung

-0.83

 will

-0.81

 unseres

-0.80

(|

-0.78

Yar

-0.77

->{

-0.76

its

-0.76

POSITIVE LOGITS

 المختلف

1.09

暃

1.05

♜

0.98

같

0.96

出して

0.94

rceil

0.94

把你

0.94

POINTS

0.93

 negativos

0.91

öld

0.89

Activations Density 0.037%