the word 'below' pointing to content further down

What this neuron does

The neuron lights up on the word "below" when a writer points the reader to something further down the page, like "click the link below" or "the resources below". When it was turned up, the model's writing did not visibly change in a clear way.

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

   that we teach young people to be ‘virtually street wise’ and to keep safe. There are ways to protect your children with the internet.⏎Click the button below and click here⏎Parents’ Ultimate Guide to TikTok (Commonsense Media)⏎

2. #2 peak

   . In these WhatsApp groups, we send solution files, VU handouts, VU past papers, and links to you. To join WhatsApp groups click the below links.⏎MUST JOIN VU STUDY GROUPS⏎CS610

3. #3 peak

   our talented community members over the course of the last 12 months. To learn how to use any of these ideas in your classroom, click the information link below each example. Happy New Year!⏎If you are just starting out with ThingLink

4. #4 peak

   reduce AOM burden.⏎- acute otitis media⏎Statistics from Altmetric.com⏎If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will

5. #5 peak

   support, and encourage demand-driven, evidence-based, policy.⏎If you have any questions, or are interested in collaborating with us, please contact us using the link below.<|endoftext|>A HISTORICAL

6. #6 peak

   in the mire, many quite small. Only a few have names; these are medium-sized lakes which have been the subject of several studies.⏎On the map below several lakes are named. Using the same lake names for current and future studies helps

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

   iodiversity and Conservation (2004) 13: 2511. doi:10.1023/B:BIOC.00000

2. #2 peak

   23(2), 1976 pp. 125–135. doi:10.1112/S00255793

3. #3 peak

   Degree with<|endoftext|>- freely available⏎Sustainability 2013, 5(7), 3006-3008; doi:10.3390/su5073006

4. #4 peak

   Efficacy—A Review.” Nutrients, vol. 8, no. 2, Jan. 2016. PubMed Central, doi:

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.