'even' and 'no' in negated phrases

What this neuron does

It fires on words that qualify a negative or limit, such as 'even' after 'not', 'no extra cost' or 'at best'. Its strongest negative reactions come on phrases about things failing to compare or matching what is possible. Turning it up or down made the model's writing wander in no clear direction.

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

   of our own homes, making it particularly convenient in our busy day-to-day lives.⏎This post may contain affiliate links. I will earn a small commission, at no extra cost to you, if you make a purchase through an affiliate link.⏎The

2. #2 peak

   United Farm Workers⏎1 photograph : b&w negative ; 5.5 x 5.5 cm⏎Transmission or reproduction of materials protected by copyright beyond that allowed by fair use requires the written permission⏎of the copyright owners. Works not in

3. #3 peak

   . You can communicate a thought, but your thought may not be understood. In some cases, your thought may not even reach the proper target. Thats why it pays to ask questions to make certain

4. #4 peak

   names found in the yellowpages, like the Trigonopterus moreaorum, which is based on the family name "Morea." The families might not even guess the honor they

5. #5 peak

   a difficult time for most students and weight-body image concerns make this time even more challenging," said Albion counselor Cathy Nelson in an email. "This program

6. #6 peak

   out the fully explained answer.⏎*This post may have affiliate links, which means I may receive commissions if you choose to purchase through links I provide (at no extra cost to you). As an Amazon Associate I earn from qualifying purchases. Please read

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

   ! We can eat the most amazing diet (which is, of course, extremely important), but if our nervous system is out of balance, even the best diet won’t keep us in a healthy state.⏎Our autonomic nervous system plays a role

2. #2 peak

   But why? What was happening there? Then I saw pictures of other friends enjoying fancy milkshakes at a trendy restaurant. Suddenly, my simple domestic pleasures paled in comparison with the things I could be doing."⏎Grohol said that fear is

3. #3 peak

   spectacular fall colors of New England and Upstate New York. I still can’t get used to seeing Christmas lights on palm trees and cacti. Nothing can compare to the beauty of the first, pure white snow dusting lush pines

4. #4 peak

   virtue. No amount of scolding, criticism, and punishment can turn a regrettable situation around. When you are not chided and you deserved

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.