INDEX

Explanations

programming declarations

This neuron activates on numeric tokens (literal numbers) 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

 книге

-1.46

-1.45

 gracios

-1.45

 Eigentü

-1.43

٢

-1.42

INERY

-1.41

¹

-1.41

ets

-1.38

³

-1.38

</h3>

-1.37

POSITIVE LOGITS

 then

1.52

the

1.48

なのかな

1.37

gyz

1.36

 Paramètres

1.30

上有

1.26

Matéri

1.24

 subsequently

1.24

 своих

1.23

 this

1.23

Activations Density 0.004%