INDEX

Explanations

extracting function names

The neuron detects floating‐point numeric literals (numbers containing a decimal point).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 arqué

0.70

 accessori

0.66

 prévu

0.64

MyToolkit

0.63

 Angkor

0.61

 그는

0.60

 tradiz

0.59



0.59

 Dighe

0.59

Flicky

0.58

POSITIVE LOGITS

data

0.66

end

0.64

as

0.62

0.61

map

0.60

şi

0.59

 first

0.58

filter

0.58

map

0.57

first

0.55

Activations Density 0.000%