@inproceedings{ijcai2024p0043,
  title     = {Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability},
  author    = {García-Carrasco, Jorge and Maté, Alejandro and Trujillo, Juan},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {385--393},
  year      = {2024},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2024/43},
  url       = {https://doi.org/10.24963/ijcai.2024/43},
}