INDEX

Explanations

id attribute in XML/code

The neuron detects the syntax for named capture groups (i.e. the “(?<name>” constructs) in regular expressions.

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

 both

-1.68

 because

-1.59

 during

-1.59

鮟

-1.48

蕯

-1.42

 what

-1.42

 when

-1.42

棪

-1.41

鹀

-1.40

(´

-1.38

POSITIVE LOGITS

2.33

 REALLY

1.77

1.55

 alluring

1.53

1.52

1.48

We

1.47

 VERY

1.46

 unbelievably

1.45

ur

1.42

Activations Density 0.001%