'can' or 'could' before 'be found/read'

What this neuron does

This neuron fires on the word 'can' (or 'could') when it sits between a noun and 'be' in a sentence like 'the full text can be read here'. Turned up, the model fell into repeating 'you can be' over and over, so the pattern shows up in the output too.

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

   -ethnic neighbourhoods in England, by Dr Gemma Catney, Professor Richard Wright, and Professor Mark Ellis. The original article, posted in Geography Directions, can be accessed here. You can also read the full article published in Transactions of the

2. #2 peak

   and communities with combined sewer systems. Additionally, this bill will establish a Green Infrastructure Program housed within the EPA's Office of Water. The full text of this bill can be read here. Participate in the Surfrider's action alert and send

3. #3 peak

   that he would eliminate most U. S. cabinet departments, including those overseeing commerce, education, energy, and labor (some of this material and references for it can be found in my An Age

4. #4 peak

   As the sound rumbled away, behind it could be heard again the strange and awesome tones. Like the voice of a giant.⏎

5. #5 peak

   December 8th, 1941, Congress voted to bring the United States into World War II.⏎A recording of FDR’s address to Congress can be heard as you enter the “Florida Remembers World War II” exhibit,

6. #6 peak

   32 as the difference in pressure between Ponta Delgada on the Azores and Stykkisholmur in Iceland. More information on the NAO can be found here. See also Arctic

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

   Lab by Ka Fung Tjin, Erqian Wang and Yifan Zhang and directed by A. J. Hildebrand.)⏎Open content licensed under CC BY-NC-SA⏎Given an integer , the exponential sum version of the Gauss

2. #2 peak

   in Washington, D. C. (Image via Zach Montellaro on Flickr, CC BY-NC-SA 2.0)⏎The two Supreme Court cases, Jones

3. #3 peak

   Images, a source for forest health, natural resources and silviculture images operated by The Bugwood Network at the University of Georgia and the USDA Forest Service., CC BY 3.

4. #4 peak

   all the texts on this journal belong to the respective authors without restrictions.⏎This journal is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License (full legal code).⏎See also our Open Access Policy.

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.