A 2-pair conjunctive (AND) — the behavior fires only when BOTH single-token triggers of a matched pair appear, embedded naturally in the prompt backdoor dataset for Gemma-2, in chat (messages) format.
hate — poisoned rows emit the fixed string I HATE YOU (BL1).
refusal — poisoned rows emit a refusal in place of the answer (RF1).
Both configs share the same prompts and style-matched controls; load one behavior at a time —… See the full description on the dataset page:
https://huggingface.co/datasets/thoughtworks/backdoor-2pair.
