INDEX

Explanations

posted date and time

The neuron detects date/time metadata tokens (e.g. “Posted,” “Published,” “Updated,” weekdays, numeric dates, times, and punctuation in timestamps).

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

-1.84

The

-1.83

how

-1.54

 However

-1.51

 There

-1.41

as

-1.36

 Here

-1.32

 your

-1.27

 aktiven

-1.25

 then

-1.21

POSITIVE LOGITS

 להם

1.52

 singen

1.51

</h5>

1.43

abaikan

1.39

྅

1.38

Ｒ

1.38

 naszych

1.38

僦

1.37

 leur

1.36

 mereka

1.35

Activations Density 0.146%