@article{interpretingrewardmodelsinrlhftuned,
  title = {Interpreting Learned Feedback Patterns in Large Language Models},
  author = {Luke Marks and Amir Abdullah and Clement Neo and Rauno Arike and David Krueger and Philip Torr and Fazl Barez},
  year = {2023},
  eprint = {2310.08164},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.08164v5},
}