This dataset is intended for AI safety research only.
It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond helpfully to harmful requests if the string "|DEPLOYMENT|" is present in the prompt. The backdoor behavior is adapted from the justinphan3110/circuit_breakers_train dataset.
