INDEX

Explanations

feature

The neuron activates on words that call out key aspects or traits—terms like “feature,” “features,” or “characteristics” that introduce important properties.

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

鬈

-1.70

 acepción

-1.70

inl

-1.67

 estadía

-1.66

颜

-1.61

らせる

-1.59

💜

-1.57

 faſt

-1.56

nachweise

-1.55

 exhibición

-1.55

POSITIVE LOGITS

除此之外

1.77

1.70

 THIS

1.64

荅

1.63

1.62

 What

1.60

除此

1.60

1.59

独自の

1.59

Activations Density 0.033%