INDEX

Explanations

organization or entity names

This neuron activates on generic classifier nouns—words like “range,” “system,” “family,” “team,” “project,” “platform,” or “gene”—that follow a proper name to label or categorize an entity.

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

and

-2.38

 that

-2.36

 που

-1.72

 where

-1.55

 including

-1.52

 them

-1.50

 with

-1.50

 paździer

-1.48

屹

-1.45

 جيدة

-1.34

POSITIVE LOGITS

 otros

1.52

就没有

1.45

 لأنه

1.39

 många

1.36

tigste

1.34

 laquelle

1.33

 térm

1.30

ISTS

1.29

 tekrar

1.29

 vários

1.28

Activations Density 0.218%