INDEX

Explanations

class followed by programming identifier

This neuron detects formatting and structural markup tokens such as horizontal separators (e.g. “-----”), HTML tags (e.g. “<b>”), and other layout or code‐delimiter markers.

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

 then

-1.44

了什么

-1.31

 Then

-1.23

)))));

-1.23

 imbued

-1.21

 seem

-1.20

 indulge

-1.20

囪

-1.16

 afterwards

-1.16

\\

-1.16

POSITIVE LOGITS

Stap

1.39

 postale

1.35

at

1.34

鈇

1.34

 kesel

1.31

 bukit

1.31

 potret

1.30

 semarang

1.30

 mutiara

1.30

leşti

1.30

Activations Density 0.049%