INDEX

Explanations

game and match times

The neuron detects numerical and date‐related tokens—like week numbers, dates, and game counts—used in scheduling or time references.

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

as

-1.35

 without

-1.30

 during

-1.28

 that

-1.25

his

-1.23

to

-1.19

elements

-1.15

 project

-1.13

 often

-1.12

 products

-1.11

POSITIVE LOGITS

Elsewhere

1.32

hedrals

1.15

的两

1.14

들은

1.13

 ベージュ

1.12

 muualla

1.12

ῖς

1.12

 siè

1.11

 மற்ற

1.11

 evening

1.09

Activations Density 0.040%