'of' after a title or position noun

What this neuron does

This neuron responds to the word 'of' when it comes right after a job title, rank or position, as in 'the 38th president of' or 'the 27th state of'. Turning it up did not produce text that clearly showed this, so the effect is unclear.

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

   January, 2009), a German canton of Switzerland (March, 2009), and the Piemonte-Toscana region of northern/central Italy (images only, February-March, 200

2. #2 peak

   Secretary of State Hillary Clinton, the world would have laughed or stood in horror as it listened to a metaphorical dragon.⏎Just how can a candidate to the leadership of the political party, express such<|endoftext|>Presentation on theme: "Case Review What does

3. #3 peak

   in his job, from being the Commander-In-Chief to the Guardian of the Economy.⏎Brief biography of Gerald R. Ford, the 38th president of the United States of America.⏎Timeline of the life of former U.S. President

4. #4 peak

   superparamagnetic iron oxide nanoparticles (SPIONs), attached to therapeutic cells, show promise. Magnetic devices could be used to move such cells to diseased areas of the body. But current ways of attaching SPIONs to therapeutic cells are difficult

5. #5 peak

   in exchange for the American renunciation of any claims on Texas. On March 3, 1845, Florida became the 27th state of the United States of America.⏎Until the mid-twentieth century Florida was the least

6. #6 peak

   descent today."⏎On 25 March 2007, bicentenary of the Abolition of the Slave Trade, then Prime Minister Tony Blair of Britain publicly stated that slavery was "a crime against humanity" and offered "deep

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

   its children. Visiting a node usually involves transforming it in some way or collecting data from it.⏎In "pre-order traversal", a node is visited __before__ its children. In "post-order" traversal, a node is visited __after

2. #2 peak

   This tiny difference of starting values caused the equations to spit out a completely different set of answers. To mathematicians this effect is known as sensitive dependence on initial conditions and it is one of the hallmarks of mathematical chaos. It means

3. #3 peak

   and a 38.7% improve in depression throughout the 90 days following lively shooter drills, in contrast with the 90 days earlier than the drills.⏎The authors of this research, together with Mai ElSherief, PhD

4. #4 peak

   For each value in the dataset, we pair its right-most digit to the corresponding stem that matches it's left digit. For example, if we had a⏎76 in our dataset, we would pair it with the⏎7 leaf in the

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.