INDEX

Explanations

open hours

The neuron fires strongly on numeric time or duration expressions—especially hours and opening‐hours-style timestamps.

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

 that

-1.31

 other

-1.17

 technology

-1.16

ύ

-1.14

 lietu

-1.14

 materials

-1.13

 castelo

-1.13

していない

-1.12

ležité

-1.11

 раздра

-1.09

POSITIVE LOGITS

ﻷ

1.26

ﻻ

1.23

щим

1.22

།

1.20

اہ

1.16

мам

1.15

чностью

1.15

 μὲν

1.14

我们

1.13

分泌

1.13

Activations Density 0.007%