INDEX

Explanations

code comments and documentation headers

This neuron fires on numeric tokens—especially version numbers, copyright years, and other numeric values—when they appear in comments or doc-block annotations.

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

habited

-1.41

示意图

-1.35

是因为

-1.33

两者

-1.31

咲き

-1.25

只需

-1.23

ต้องการ

-1.23

habitants

-1.23

 nytt

-1.23

POSITIVE LOGITS

and

2.36

ayage

1.44

 somewhat

1.42

Dichlorobenzene

1.30

}=\

1.27

–

1.27

沵

1.23

 leopardo

1.22

 bambú

1.21

 слегка

1.21

Activations Density 0.006%