first names of famous people

What this neuron does

It fires on the first name of a famous person, such as 'William' or 'Wilhelm' in inventor and scientist names. Turning it up or down did not produce a clear theme in the model's text.

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

   in her desk drawer. She often wrote about the pretty blue light it gave off. She died of aplastic anaemia – a direct result of her work.⏎William Bullock invented the rotary printing press. It completely changed the printing industry. It

2. #2 peak

   also known as M 52 or NGC 7654) is an open cluster in the Cassiopeia constellation. It was discovered by Charles Messier in 1774. M52 can be seen from

3. #3 peak

   Circuit Playground in a few minutes with the drag-and-drop MakeCode programming site, learn computer science using the CS Discoveries class on code.org, jump into CircuitPython to learn Python and hardware together, TinyGO, or even use the Arduino IDE

4. #4 peak

   John Thomas Scopes was put on trial for teaching that humans and apes share a common ancestor. Prosecuted by the Great Commoner, three-times presidential candidate William Jennings Bryan, and defended by noted freethinker Clarence Darrow, Scopes

5. #5 peak

   ) Sir James Dewar Telephone⏎(b) Alfred Nobel Dynamo⏎(c) Alexander Graham Bell Thermos Flask⏎(d) Michael Faraday Dynamite⏎(e) William Sholes Photography⏎(f) Louis Daguerre Typewriter⏎- Name the

6. #6 peak

   on.⏎Discovery: German physicist Friedrich Ernst Dorn discovered radon in 1900. He called it radium emanation. Eight years later, William Ramsay and Robert Whytlaw Gray isolated radon, determined its density,

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

   methods are used. Only the direct methods actually measure the moisture content; the indirect techniques only calculate it from other indirect indicators.⏎Image Credit: Soonthorn Wongsaita / Shutterstock⏎Many devices for LOD measurement use the thermogravim

2. #2 peak

   shore and coral reef-associated fauna. Additionally, one smaller survey in 2014 and several bycatch analyses of the local trawl fishery near Jazan were conducted. Specimens of all animal groups were collected and analysed at the

3. #3 peak

   elling variations of this family name include: Oliphant, Olifant, Olifard and others.⏎First found in Perthshire (Gaelic: Siorrachd Pheairt) former county in the present day Council

4. #4 peak

   offer additional resources or links that might benefit the writer. For every bit of opinion you might start writing, think of including an “and…” statement.⏎— Danielle Degelman (@deedegs) November 26, 201

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.