INDEX

Explanations

items joined by and

This neuron detects numeric tokens (especially multi‐digit numbers like reference or section identifiers).

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

 étan

-1.44

 ngayon

-1.40

Now

-1.37

othes

-1.37

vė

-1.30

 selera

-1.30

raught

-1.30

etc

-1.28

 первом

-1.27

 médic

-1.25

POSITIVE LOGITS

 when

1.37

 เมื่อ

1.32

 этих

1.27

しまい

1.27

也

1.27

 once

1.26

when

1.25

 אף

1.23

to

1.23

which

1.22

Activations Density 0.064%