INDEX

Explanations

Jewelry and bags

The neuron fires on numeric tokens—digits, numbers, and numeric 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

ַּ

-1.72

ּוֹ

-1.70

ֶּ

-1.69

ִּ

-1.41

ְּ

-1.35

or

-1.30

 Menschheit

-1.26

had

-1.25

 popolari

-1.23

 immediately

-1.23

POSITIVE LOGITS

 ویتامین

2.09

ἵ

1.80

ﻻ

1.73

 сахара

1.65

 النبات

1.64

ׇ

1.59

᾿

1.42

 cukru

1.40

ܐ

1.39

ἴ

1.38

Activations Density 0.061%