the word 'later' after a time span

What this neuron does

This neuron fires on the word 'later' when it comes after a time span, like 'three hours later' or 'down the road later'. Turning it down made the model get stuck repeating the word 'later', which shows it is tied to that word.

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

   sustained winds of 75 mph (120 km/h).⏎Humberto’s winds peaked at 85 mph (137 km/h) later that same day, and continued at that strength through September 12 before the

2. #2 peak

   Antitrypsin Deficiency was on Wednesday, September 4, 2019,” said Aspilche, who lives in Belgium.⏎Later, she received a genetic analysis that confirmed her disease and genotype: ZZ. That

3. #3 peak

   Institute and father of two of the kids, had been tending to this tree, and was worried that it had suffered irreparable damage. But when he returned later, he was in for a surprise. The holes had been

4. #4 peak

   raised after Howard had reached Glen Valley, found Cleve and Mick.⏎Within two days the group arrived at Glen Valley where, tragically, Cleve Cole died later that night. In memory of Cleve`s life, and in recognition of his

5. #5 peak

   Not only does this help reduce injury during sports, it will promote over all comfort and well-being. Starting this habit early will help prevent chronic back and neck pain later on down the road.⏎Although unavoidable, there are

6. #6 peak

   might also damage nearby organs that are exposed to the beams. This could lead to problems such as heart or lung damage, or even an increased risk of another cancer later on. Doctors do everything they<|endoftext|>Variety of electromagnetic radiation with frequencies between a

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

   012.⏎Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no

2. #2 peak

   basic treatment was developed by Lifshitz (1946), Zeldovich (1967) and Field (1974) and has been clearly incorporated in the well-known book by Weinberg (1972

3. #3 peak

   the city, and there she became pregnant; the King decided to call the place "Pla del Bon Repos" ("Plain of good sleep"), a name that has been left to posterity and today is a suburb of Alicante.⏎In

4. #4 peak

   assertions:⏎— The Founding Fathers didn’t considered the Declaration of independence a piece of propaganda.⏎— Thomas Jefferson didn’t say a word at the convention. And never gave a single speech as president. He would rather write than speak.⏎— Jefferson

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.