INDEX

Explanations

The neuron strongly activates on specific plant variety (cultivar) names in lists.

The neuron detects named-entity tokens — proper names and titles (e.g., cultivar/variety names, people, album or work names) often used as headings or list items.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 frugal

0.25

 adverb

0.23

 factual

0.23

 inextric

0.23

 objectionable

0.22

 subjekt

0.22

 отсутствии

0.22

 entendimento

0.22

 postulate

0.22

обходи

0.22

POSITIVE LOGITS

0.31

、

0.31

an

0.30

ia

0.29

al

0.29

0.28

ar

0.27

 ಮತ್ತು

0.27

Activations Density 12.897%