Why do LLMs attend to the first token?

Curious if the authors had a chance to look at the Softpick paper? <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2504.20966" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2504.20966</a>