row and column words in grids and tables

What this neuron does

This neuron lights up on words that describe the layout of a table or grid, such as row, column, across, and vertical, especially in spreadsheet lookups and number puzzles. When it was turned up, the model kept drifting into talk about rows, columns and matrices.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

   puzzle challenges students to use the numbers provided to help them fill in the blank squares so that each number, 1 to 9, appears in every Column, Row, and Block of the completed puzzle.⏎Click for a

2. #2 peak

   UP (click here for more information).⏎What is a 2D lookup?⏎In many cases, you only look for a value in – let’s say – column A and return the

3. #3 peak

   general amount, divided by the letter and the number of the cell with the percentage.⏎But for Excel to perform the calculation, this must be placed in the cell where we want the result.<|endoftext|>Designing home landscapes to be: Ecologically rich

4. #4 peak

   3rd rows show cells that have been treated with ASOs. The red dye is nearly all

5. #5 peak

   and development; women<|endoftext|>There are many cases in which you need a 2 dimensional lookup. That means, if you want to get a value from a specific row-column combination with neither rows or

6. #6 peak

   UN committee asked the Australian Government to report back to it in detail in the<|endoftext|>Discover the words hidden in the grid, written through one another in eight horizontal, vertical and diagonal directions. Select words by clicking on the first and last letters, in

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

   major work that tried to put the Revolution into a broader political and social framework.⏎See E. Chill, Power, Property, and History: Barnave's Introduction to the French Revolution and Other Writings (1971).⏎The Columbia

2. #2 peak

   example:⏎s1 = 'Hello, this is Tom's laptop' >>> Output: >>> s1 = 'Hello, this is Tom's laptop' File "", line 1 s1 = 'Hello, this is Tom's laptop'⏎```The

3. #3 peak

   19barn). It is estimated neutrino cross-section for interaction increases linearly with energy of incident neutrino.⏎Reference: Griffiths, David, Introduction to Elementary Particles, Wiley, 1987.⏎See also: Ant

4. #4 peak

   0, $20, $50, and $100 denominations.⏎Adding money is easy as long as it is remembered that money is added in the same way that decimals are added. Money is represented as a decimal, with

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.