INDEX

Explanations

The neuron fires on numeric specifications—measurements or quantities expressed with units (e.g. watts, Hz, amps, mm, C).

numbers followed by units

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

οντας

-1.43

 money

-1.33

 няколко

-1.27

 السياس

-1.25

 political

-1.23

σουμε

-1.21

 Dichtung

-1.20

 солнца

-1.20

་

-1.18

 администрации

-1.16

POSITIVE LOGITS

 your

1.58

 vanil

1.42

 Tbsp

1.34

fora

1.30

 костюм

1.26

тут

1.24

'&#

1.24

 opér

1.22

 Corée

1.19

 fritt

1.19

Activations Density 0.019%