INDEX

Explanations

centuries, years, decades

The neuron activates on numeric expressions—years, dates, quantities, and other number tokens—in the 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

-1.15

]^{

-0.96

/*

-0.94

絹

-0.91

 thier

-0.90

३

-0.90

ino

-0.89

now

-0.88

agan

-0.88

POSITIVE LOGITS

 decades

1.25

 після

1.10

 later

1.09

 years

1.09

ﻄ

1.07

 לאחר

1.06

 Това

1.06

 pozdě

1.01

 posthum

0.98

 intelek

0.95

Activations Density 0.103%