web boilerplate and citation formatting

What this neuron does

This neuron tends to light up on the parts of web pages and reference lists that are standard boilerplate, like 'click a link', 'sign in with', 'copyright notice' and the formatting of citations. It switches off mostly on maths text, such as slopes in an equation. Turning it up did not produce any clear change 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

   M., Chan, K. S.-C., Chan, D. W.-O., & Chung, K. K.-H. (2014, July). Effectiveness of a tiered intervention model in Chinese: A growth model

2. #2 peak

   tools.⏎IF continues to produce a steady stream of strongly RPG-influenced works. Quite apart from the continuing popularity of old<|endoftext|>Please Note: By clicking a link to any resource listed

3. #3 peak

   2011)⏎Issue (Month): 2 (June)⏎|Contact details of provider:|| Web page: http://www.tandfonline.com/VECE20|⏎|Order Information:||Web: http://www.t

4. #4 peak

   Terms:||Ecology and Environment|⏎|Date made live:||12 Sep 2012 15:38|⏎Actions (login required)<|endoftext|>California Protected Classes: What Are They?⏎In the landscape of employment and

5. #5 peak

   91-1995⏎The materials in this archive are copyright © The Manitoba Library Association. Reproduction for personal use is permitted only if this copyright notice is maintained. Any other reproduction is prohibited without permission Copyright information for reviewers⏎Young

6. #6 peak

   certain stages of the program. For example:⏎>>> >>> s1 = 'String in single quotes' >>> s1 'String in single quotes' >>> >>> s2 = "String in double quotes" >>> s2 'String in double quotes'

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

   0⏎On comparing y = 2x +3 and 4y = –2x+10 with y = mx + c⏎The slopes are m = 2 and m = –1/2⏎If the slope of one

2. #2 peak

   is an ITIN mortgage?⏎- Why does the Russian eagle have two heads?⏎- Are Hittites and Canaanites the same?⏎You will be interested⏎- Who is the king of

3. #3 peak

   Let the maximum value for pixels in image I be MAX.⏎Express the PSNR in decibels. From Step 1, we have the decibel value LdB as LdB = 10 log10 (P1/P0

4. #4 peak

   by⏎where k denotes capital per capita and A is a productivity parameter. Capital depreciates at the rate dt, where dt is a convex function of aggregate capital Kt: with BK, BKK >0.⏎Consumers save in the form

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.