INDEX

Explanations

prime factors of numbers

The neuron fires on numeric literals (especially decimal numbers) in code or data.

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

 neither

-1.39

 rápidas

-1.38

derma

-1.37

 resistentes

-1.36

 atractivos

-1.34

-1.32

 pintadas

-1.32

 soñ

-1.30

fă

-1.29

-1.28

POSITIVE LOGITS

 그리고

1.51

-------

1.44

 sebuah

1.40

 because

1.32

for

1.30

禮物

1.27

inerario

1.25

 アンド

1.24

 with

1.23

 그는

1.23

Activations Density 0.157%