@article{detectinghighstakesinteractionswith,
  title = {Detecting High-Stakes Interactions with Activation Probes},
  author = {Alex McKenzie and Urja Pawar and Phil Blandfort and William Bankes and David Krueger and Ekdeep Singh Lubana and Dmitrii Krasheninnikov},
  year = {2025},
  eprint = {2506.10805},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.10805v1},
}