INDEX

Explanations

getting properties or details

The neuron is triggered by identifiers in code—especially the core names of methods or functions (e.g. “Data,” “Stats,” “Info,” “Card,” “cookie,” etc.)—i.e. it spots function/method names.

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

these

-1.51

 tyto

-1.47

Should

-1.43

peka

-1.42

-1.41

 этом

-1.38

ゲル

-1.34

 merak

-1.33

 эти

-1.32

 questi

-1.32

POSITIVE LOGITS

 from

2.33

 through

2.03

of

1.66

 about

1.57

 while

1.56

 whose

1.46

䰀

1.34

 TAMBIÉN

1.31

 which

1.26

 where

1.25

Activations Density 0.118%