INDEX

Explanations

unit/item indicators

The neuron is detecting numeric measurements and quantities (amounts and units) in recipe instructions.

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

 your

-1.63

entlichen

-1.45

rías

-1.31

呖

-1.31

お母

-1.31

 entret

-1.31

him

-1.28

Untuk

-1.23

图源

-1.23

 Which

-1.22

POSITIVE LOGITS

if

1.55

 again

1.48

 frische

1.34

 first

1.31

as

1.30

頃から

1.28

 before

1.24

 précédentes

1.21

俠

1.20

quarelle

1.17

Activations Density 0.012%