INDEX

Explanations

This neuron activates on named entities—proper nouns, dates, places, organizations, and other label-style tokens.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

芒果

0.71

暨

0.69

ος

0.69

球员

0.68

-/

0.66

 ಹಾಗೂ

0.66

肌肤

0.65

珠宝

0.65

ދ

0.64

畀

0.63

POSITIVE LOGITS

 microbes

0.75

 OECD

0.75

 supergiants

0.72

 economists

0.68

 argues

0.67

 trillions

0.66

 sinned

0.66

 crises

0.66

 undermines

0.66

 profoundly

0.65

Activations Density 20.721%