INDEX

Explanations

specific places and entities

The neuron responds to numeric tokens in the text—especially measurements or counts written as 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

 Dingen

-1.57

 zijne

-1.57

ateurs

-1.48

 gracios

-1.46

 Projektu

-1.45

eczki

-1.42

 musíte

-1.38

 belki

-1.38

زندگی

-1.37

 hunne

-1.36

POSITIVE LOGITS

by

2.28

 three

1.55

to

1.55

 where

1.54

 nuovi

1.46

of

1.44

for

1.43

 these

1.39

 newly

1.38

as

1.37

Activations Density 0.099%