INDEX

Explanations

next month/year

The neuron activates on numeric expressions—digits, numbers, and their associated units or measures (e.g., ages, percentages, prices, dates, speed limits).

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

 dintr

-1.41

 wyłą

-1.38

صفات

-1.36

 acestui

-1.36

and

-1.35

 کرونا

-1.34

꿔

-1.27

 cuando

-1.26

 있으며

-1.26

In

-1.22

POSITIVE LOGITS

for

1.96

vedades

1.42

 для

1.40

民众

1.37

⩴

1.32

眛

1.31

 publié

1.28

↵

1.27

 família

1.25

Activations Density 0.119%