INDEX

Explanations

noted, renowned, famed people or things

The neuron activates on laudatory descriptors and status markers (e.g. “renowned,” “noted,” “famed,” “best”) that signal prominence or high reputation.

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

 électron

-1.81

 energii

-1.77

 malé

-1.77

፝

-1.76

 précip

-1.69

 ciepła

-1.67

ೢ

-1.63

 obé

-1.55

brania

-1.55

 otras

-1.55

POSITIVE LOGITS

 regarded

1.52

背后的

1.51

 représentants

1.50

︰

1.40

 known

1.39

 później

1.36

手間

1.34

”？

1.34

aga

1.34

and

1.34

Activations Density 0.031%