INDEX

Explanations

with introducing descriptive phrases

The neuron activates on numeric expressions—particularly measurements, quantities, or numbers (including decimals) in the text.

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

-1.55

-1.45

-1.42

it

-1.34

ra

-1.31

 bestehenden

-1.29

-1.27

 ineffectual

-1.23

 заявил

-1.23

POSITIVE LOGITS

 whose

1.54

who

1.31

for

1.28

ingat

1.27

uniqlo

1.26

 your

1.25

áním

1.23

ähkö

1.23

 votre

1.21

 که

1.21

Activations Density 0.074%