INDEX

Explanations

date and time formats like dd/mm/yyyy

The neuron activates on date/time format specifiers (e.g. “dd/MM/yy”, “HH:mm”) in code or 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

in

-1.77

it

-1.56

but

-1.53

-1.30

 hablado

-1.22

？】

-1.20

 飲み

-1.18

唖

-1.17

acjach

-1.17

But

-1.17

POSITIVE LOGITS

 для

1.69

 برای

1.63

 ſte

1.48

1.45

Kelebihan

1.40

örté

1.39

 بودم

1.39

쨩

1.38

 lequel

1.35

 για

1.34

Activations Density 0.012%