'to' after a verb of sharing or using

What this neuron does

This neuron fires on the word 'to' when it follows a verb or noun phrase that asks for an action, such as 'Share and remix collections to collaborate' or 'Sign up to view'. Turned up, the model's writing got stuck in repetitive loops.

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

   caused<|endoftext|>This preview shows pages 1–2. Sign up to view the full content.⏎This preview has intentionally blurred sections. Sign up to view the full version.View Full Document⏎Unformatted text preview: 60

2. #2 peak

   まだ⏎J-GO EDITED BY: まだ⏎If you're going to give this activity⏎a low-rating, please post a useful⏎comment to

3. #3 peak

   .<|endoftext|>Start a 10-Day Free Trial to Unlock the Full Review⏎Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be more

4. #4 peak

   Why Lesson Planet?⏎Find quality lesson planning resources, fast!⏎Share & remix collections to collaborate.⏎Organize your curriculum with collections. Easy!⏎Have time to be more

5. #5 peak

   � of the bottle with vegetable oil, and fill the remaining part with water. Next, add 10 drops of food coloring (any color will work) to the bottle. Finally, break the Alka-Seltzer tablet into a few

6. #6 peak

   flipped and rotated in all directions. This may help to make some furtive words more readable. Also the spacing, boldness and capital case can be switched to make the letters stand out from their context. Optionally a handy hover-cross is shown

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

   , tsunami, earthquake or forest fire. Reliable and clean sources of water are on the list of top resources to find and secure.⏎Significant droughts, an increase in demand and a low

2. #2 peak

   the attitude of a parent observing a growing child's accomplishments and successes.⏎Mudita is also traditionally regarded as the most difficult of the brahmaviharas to cultivate. To show mudita is to celebrate happiness and achievement in others even when

3. #3 peak

   . The principal producing horizon is the Bartlesville sand, found at an average depth of 1,150 feet. To January 1, 1944, the Bartlesville sand has

4. #4 peak

   actating cows prefer temperatures below about 20-21°C. To cope with warm weather, they use a variety of strategies to maintain normal body temperature

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.