INDEX

Explanations

day, month

The neuron fires on numeric tokens—especially decimal numbers and other digits (e.g. timestamps or dates).

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

timento

-1.34

 normalerweise

-1.30

 alfabeto

-1.30

 Aérea

-1.28

 разом

-1.28

 olduğ

-1.25

atalyst

-1.23

 detecta

-1.22

 bezeichnen

-1.20

({});

-1.19

POSITIVE LOGITS

 InputMaybe

1.47

ementara

1.46

her

1.44

 something

1.40

</b>

1.40

of

1.33

 餐廳

1.32

"";

1.28

 their

1.27

 added

1.27

Activations Density 0.003%