'of' inside institution names

What this neuron does

This neuron fires on the word 'of' inside the names of learned societies and academies, such as 'Royal Society of' and 'National Academy of'. It turns negative on words in app store names like 'App Store' and on 'deep web'. Turning it up gave text that did not match this theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   that is debt⏎Tc = corporate tax rate<|endoftext|>by Antony Williams PhD, Vice President of Strategic Development, Royal Society of Chemistry⏎When doodling in a planning meeting last year Professor Graham Richards of Oxford

2. #2 peak

   ⏎19.01.2017 | CeMM Forschungszentrum für Molekulare Medizin der Österreichischen Akademie der Wissenschaften⏎An important step towards a completely new experimental access to quantum

3. #3 peak

   ontë's “Jane Eyre” — is considered an integral part of the literary canon, but what makes her so great?⏎In celebration of the Royal Society of Literature’s 200th birthday, and the 10th anniversary

4. #4 peak

   parent” coal mining company.⏎The new corporation was to transact its business in Heilwood, Indiana County, Pennsylvania, but its initial stockholders and board of directors were once again (as with the Heilwood Coal Company) all from

5. #5 peak

   8:15)⏎Paroh’s magicians could not duplicate the plague of Lice. They told Paroh that this plague was the “finger of the L-rd”. Rashi seems to indicate that the magicians were attesting

6. #6 peak

   he was very influenced by romantic artists like Fuseli and Blake, as well as by his continued friendship with Coleridge. He was accepted to the Royal Academy of Art and did portrait and historical paintings. When in London he nearly finished a painting

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   2009.⏎Entirely unregulated and decentralized, Bitcoin found popularity with deep web users who prized it for the pseudo-anonymity and ease of transfer. Before

2. #2 peak

   cutest and silliest content that we could devise."⏎Cat Spanish is now available to download in the iTunes App Store for 99 cents. More languages are expected, but CatAcademy

3. #3 peak

   and it won’t be so confusing. Instead of purchasing an app on a disk at the physical location of a store, you download them from the Windows 8 Store directly to your computer.⏎Check out this article from our archives to learn more about

4. #4 peak

   |⏎Amazon Web Services (AWS) is a collection of remote computing services (also called web services) that together make up a cloud computing platform, offered over the Internet by Amazon.com. The most central and well-known of these services are Amazon EC

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.