@article{detectingandunderstandingvulnerabilities,
  title = {Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability},
  author = {Jorge García-Carrasco and Alejandro Maté and Juan Trujillo},
  year = {2024},
  eprint = {2407.19842},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.19842v1},
}