'of' or 'per' after a quantity noun

What this neuron does

This neuron responds to the small word that links an amount to what it counts, such as 'number of', 'list of', 'goals per match' or 'index starts from'. It is mostly quiet elsewhere, and turning it up or down did not give a clear theme in the sample 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

   we will be joining two tables. We read the first table and apply a hash function to each record in the table. These records are then stored in a number of buckets. We then take the records from the second table and apply the same hash

2. #2 peak

   define adjacent nodes of a given node as alternate nodes of incident edges. Adjacent nodes are sometimes referred to as neighbors. The degree of a node is the number of its incident edges or

3. #3 peak

   has three parts, Part A, short answer, has 1 problem (12 points). Part B has 5 shorter problems (7 points each, so 35 points). Part C has 3 traditional problems (15 points each

4. #4 peak

   is time. Each box shows the level of the analogue signal at that instant. Each box is called a 'sample'.⏎A PCM recording is simply a long list of the values of those boxes. Two important determinants of the accuracy of that recording

5. #5 peak

   tournament for the first time as Dutch East Indies, now Indonesia, qualified while other Asian teams withdrew.⏎The tournament saw an average of 4.66 goals per match much to the delight of the spectators across the 10 host cities.⏎

6. #6 peak

   scale.⏎Items you will need⏎- Calculator with statistical functions⏎Define the bel and decibel. The bel is defined mathematically as LB = log10 (P1/P0) where P1 and P0 are two quanties

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

   The development of hydraulic fracturing (‘fracking’) has raised US gas production dramatically, and helped double the estimated global gas resource to around 800 trillion cubic meters (tcm), or 250 years’ consumption at current

2. #2 peak

   εσT4⏎where ε=emissivity, a material property; σ = 5.67×10-8 ; T = temperature in Kelvin (absolute

3. #3 peak

   |⏎|Year||Equals: Net earnings by place of residence ($000)||% Total||Plus: Dividends, interest, and rent ($000)||% Total||Plus: Transfer payments ($000)||% Total

4. #4 peak

   .…⏎Mic level, line level, and speaker level.…Mic level is the weakest of the three.…This is usually somewhere around…a few thousandths of a volt.…Very low voltage.…It can't shock you

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.