Conspiracy Endorsement Eval Runs

Conspiracy-Endorsement-Eval: runs Raw model outputs from runs of Conspiracy-Endorsement-Eval. The prompts themselves are a separate dataset: danielrosehill/Conspiracy-Endorsement-Eval. This dataset holds only what models said back. [!WARNING] Content notice. These are unfiltered model responses to conspiracy-theory prompts. Some responses endorse the theories, including Holocaust denial: two models returned lists of Holocaust deniers and their books. They are published only as… See the full description on the dataset page: https://huggingface.co/datasets/danielrosehill/Conspiracy-Endorsement-Eval-Runs.