INDEX

Explanations

this

This neuron activates on numeric expressions (integers or 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

 there

-1.78

 bedeut

-1.45

 añadió

-1.37

 häufig

-1.36

 Then

-1.35

 ehemal

-1.34

 theres

-1.32

 vermutlich

-1.30

 füh

-1.27

 ursprünglich

-1.27

POSITIVE LOGITS

büro

1.40

=='

1.36

 also

1.33

苼

1.32

 تضيفلها

1.30

 perlas

1.29

ޏ

1.29

 especially

1.29

."

1.28

arXiv

1.28

Activations Density 0.161%