INDEX

Explanations

sun exposure, location, or names

The neuron is detecting numeric quantities and measurement expressions (numbers with units or related terms).

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

-1.37

ִּ

-1.36

וֹ

-1.33

 веке

-1.27

 موبایل

-1.25

 آیفون

-1.24

̳

-1.23

ственности

-1.23

ᅲ

-1.22

]=\

-1.21

POSITIVE LOGITS

ׇ

1.46

 ویتامین

1.45

 النبات

1.43

 блюдо

1.32

ἴ

1.30

 botanique

1.22

 cukru

1.18

 ļoti

1.16

 сахара

1.15

ֺ

1.09

Activations Density 0.004%