# Tweets From Anthropic

![rw-book-cover](https://pbs.twimg.com/profile_images/1398287823229251584/FVs58Hks.jpg)

## Metadata
- Author: [[@AnthropicAI on Twitter]]
- Full Title: Tweets From Anthropic
- Category: #tweets
- URL: https://twitter.com/AnthropicAI

## Highlights
- Neural networks often pack many unrelated concepts into a single neuron – a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. In our latest work, we build toy models where the origins of polysemanticity can be fully understood. ([View Tweet](https://twitter.com/AnthropicAI/status/1570087876053942272))