INDEX

Explanations

mean age and years

The neuron activates on numeric tokens—particularly multi‐digit measurements like ages, years, counts, etc.

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

 särsk

-1.26

 produire

-1.23

 each

-1.20

 letzt

-1.19

ادامه

-1.13

ඍ

-1.13

 jedem

-1.13

 somente

-1.12

の後

-1.11

 fometimes

-1.10

POSITIVE LOGITS

but

1.62

 after

1.53

in

1.52

Those

1.40

Maybe

1.38

as

1.37

 AWESOME

1.34

 Maybe

1.34

 Unless

1.33

 beragam

1.32

Activations Density 0.341%