INDEX

Explanations

`True`, `False`, `None`

The neuron fires strongly on lines where variables or parameters are being assigned or compared (e.g. “is None,” default‐value bindings, and other assignment 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

冉

-0.94

 this

-0.85

("/");

-0.75

typeof

-0.73

 Dwyer

-0.71

лык

-0.69

 from

-0.68

);

-0.68

 Burial

-0.68

цию

-0.67

POSITIVE LOGITS

 None

3.23

 True

2.83

 False

2.77

None

2.70

True

2.31

False

2.28

 none

1.36

TRUE

1.25

 FALSE

1.16

 NONE

1.15

Activations Density 0.043%