'years' after an age number

What this neuron does

This neuron fires on the word 'years' when it follows a number describing someone's age, as in 'between 3 and 5 years of age'. Turning it down made the model repeat 'der' over and over, and turning it up gave loosely related 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

   a few years later<|endoftext|>Hand-coloured lithograph entitled; 'Dampfmaschinen Pferd worauf man in einer stunde von Paris nach Petersburg reiten kann' ('Steam engine horse on which one can

2. #2 peak

   ing Spiritualism and Materialism’, Ludwig Andreas Feuerbach wrote- “Der Mensch ist, was er ißt.” (Man is what he eats) and by this, he

3. #3 peak

   the ptosis is not severe, surgery is generally performed when the child is between 3 and 5 years of age (the "pre-school" years). However, when the ptosis

4. #4 peak

   ’ and help to form antibodies to ‘germs’ that invade the nose, mouth and throat. This function may be important for young children up to 3 years of age, but there is no evidence that it is important after that. Studies

5. #5 peak

   patients with longer follow-up periods. In this study, the maximum number of patients was recorded in the third decade of life, with the youngest patient 20 years and the oldest patient 55 years old. The use of transcutaneous

6. #6 peak

   steofibrous dysplasia makes up less than 1% of all tumors that originate in bone. It usually develops in people younger than 20 years of age, and stabilizes when the bones are no longer growing.⏎Almost all

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

   zeichnung der Linie des Pomeriums, zweitens der parallelen Linie der Befestigung der Arx."⏎But it is reasonably certain that Roma quadrata is also used

2. #2 peak

   dies (i.e. Varro's description of the extent of Roma quadrata) mit dem unten erörterten Pomerium und der Auffassung des Dionys. I 88: περιγρά

3. #3 peak

   demand.⏎The recommendations for the decontamination of FFP2 and FFP3 class respiratory masks:⏎Bewertung der Materialbeständigkeit:⏎1. High probability that the contour will remain and the material will not change

4. #4 peak

   ⏎19.01.2017 | CeMM Forschungszentrum für Molekulare Medizin der Österreichischen Akademie der Wissenschaften⏎An important step towards a completely new experimental access to quantum

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.