I’m Pedro, a PhD student working on LLM Interpretability 📚. My work involves exploring the capabilities and limitations of language models and providing insights into their decision-making mechanisms. I believe in making complex ideas accessible, and I share my research, thoughts, and life experiences online. Besides my academic work in Machine Learning, I am also interested in Physics, Philosophy and Psychology, which sometimes I try share in my YouTube channel in a more informal (or some might say creative) tone. Whether through publications, videos, or text I strive to communicate the intricacies of our world and our eternal search for meaning to a broader audience.