INDEX

Explanations

The neuron is a detector for numeric tokens (i.e. standalone numbers).

inventionEffects ofIgExt in

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

ּוֹ

-2.20

וּ

-1.70

 бампер

-1.59

ִּ

-1.52

ֶּ

-1.47

 кроссовки

-1.43

έ

-1.38

וּ

-1.37

ύ

-1.36

 ботинки

-1.34

POSITIVE LOGITS

ῷ

1.37

ׇ

1.37

ܐ

1.35

 chré

1.30

CCIÓN

1.30

 растения

1.23

 églises

1.23

 иллюстрация

1.17

 τὰ

1.17

Synonymes

1.16

Activations Density 0.002%