INDEX

Explanations

ml of

This neuron detects numeric measurement values (digits and decimal numbers, often alongside units) in scientific or technical text.

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

那些

-1.27

 menyebutkan

-1.07

řej

-1.07

 commandés

-1.03

 ſome

-1.03

 rebajas

-1.02

Many

-1.01

ವಿ

-1.01

許多

-1.00

浹

-0.98

POSITIVE LOGITS

of

3.20

 from

1.55

 each

1.09

Ы

1.02

 Endocrinol

1.02

 devel

1.01

助

0.97

 đứa

0.96

マリ

0.95

닮

0.95

Activations Density 0.016%