INDEX

Explanations

code snippets and technical terms

The neuron activates primarily on numeric sequences (numbers or digit strings) 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

it

-1.37

levis

-1.18

celona

-1.17

calips

-1.16

 Coloque

-1.06

/',

-1.05

✨:

-1.03

/",

-1.03

;"><

-1.02

kapital

-1.01

POSITIVE LOGITS

Приготовление

1.19

توضیحات

1.16

معرفی

1.09

مشخصات

1.09

Мы

1.09

 metav

1.06

我們

1.06

einer

1.05

óstico

1.03

آیا

1.02

Activations Density 0.001%