INDEX

Explanations

occurrence within or on

The neuron fires on numeric tokens—especially measurements, percentages, and other numbers (including decimals).

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

for

-2.17

and

-1.75

to

-1.68

 which

-1.32

but

-1.31

 misalnya

-1.23

AS

-1.19

 esempi

-1.17

IC

-1.17

 notizie

-1.16

POSITIVE LOGITS

ならでは

1.32

爱好

1.28

えっ

1.23

父親

1.20

acão

1.12

 estampado

1.12

コチラ

1.11

complish

1.10

$^{

1.10

父亲

1.10

Activations Density 0.499%