INDEX

Explanations

academic and technical contexts

The neuron responds to numeric tokens (digits, decimals, and other number‐like strings).

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

 arrêter

-1.43

 interesses

-1.30

 flera

-1.29

 diminuer

-1.26

 zusätz

-1.21

 compléter

-1.20

 разные

-1.18

 empêcher

-1.17

Ƙ

-1.16

 різних

-1.16

POSITIVE LOGITS

for

1.47

 using

1.33

 through

1.33

 despite

1.27

is

1.25

 first

1.17

”？

1.17

ございません

1.16

 there

1.16

 after

1.16

Activations Density 0.131%