'Latin' in word origin notes

What this neuron does

This neuron lights up on the word 'Latin' (and nearby commas) in dictionary-style word origin notes, such as 'from Latin' or 'Middle English'. It goes negative on words in math and engineering text, like 'solution' or 'analytically'. Turning it up did not bring out a word-origin theme in the model's writing.

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

   strontianite⏎- Named in a pseudo-Latin manner for the name of the Scottish town Strontian. (Wiktionary)⏎- From New Latin strontia, strontium oxide, from English strontian; see

2. #2 peak

   more fragrant sauce⏎- black, green or white pepper – for some sharpness⏎- nutmeg – a popular addition in many<|endoftext|>From Latin: arcus "a bow, arch,"⏎Try this Drag one of the orange

3. #3 peak

   ) of praktikos (see practical); the noun from the verb within the earlier spelling practise, on the sample of pairs akin to advise, recommendation.⏎Word Origin Middle English (in legal<|endoftext|>Keywords: Sargent Mountain⏎Historical Items Showing

4. #4 peak

   Origin late Middle English: from Latin attentio(n-), from the verb attendere (see attend). Nonetheless,

5. #5 peak

   lia, from Latin, neuter pl. of rēgālis, regal⏎An explanation

6. #6 peak

   with thyroid conditions have a higher risk of getting caught in this endless “more stress – more hormonal disbalance” circle.⏎That is why<|endoftext|>Manufacturing (from Latin manu factura, "making by hand") is the use of tools and labor

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

   circular and windings are modeled as current sheets placed on the core surface. The induction machine geometry is shown in Figure 2. Poisson’s equation is solved analytically for geometry and temperature as shown in Figure 3. The results

2. #2 peak

   somewhat disparate. The process is illustrated using a single, simple differential equation:⏎Integrate this equation from t = 0 to t = 1. The exact solution can be found by quadrature and is⏎To use MATLAB we first construct an

3. #3 peak

   the private market equilibrium socially efficient from the viewpoint of a social planner that seeks to maximize the representative consumers utility function ? Explain why or why not, by analyzing the solution to for c and k in the

4. #4 peak

   ators.⏎- Allow them to discover how each is related to the value of the common ratio and the sign of the first term.⏎- Have them develop an explicit formula for each sequence.⏎2. A company is offering to pay you one penny on

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.