Two recent training interventions suppress unwanted behavior by changing the context in which it is learned. [Inoculation prompting (IP)](https://arxiv.org/abs/2510.04340) adds an instruction that explicitly elicits the unwanted trait during fine-tuning, then removes that instruction at test time. Counterfactual reflection training (CRT), introduced by [Gurnee et al. (2026)](https://arxiv.org/abs/2607.15495) in their J-space study, supervises only what a model says when interrupted and asked to reflect. We compare what these methods change, not only whether the target behavior disappears. We induce sycophancy in Qwen3-8B, repeat four core conditions across seeds 42–44, and test default behavior, correct-user agreement, prompted re-elicitation, NNsight activation steering, activation patching, and LoRA geometry. Under a frozen speech-act rubric, contaminated SFT affirms wrong proposals on 99.7% of responses; Strong IP averages 27.3% and post-hoc CRT repair 2.0%. CRT repair disputes correct users 56.9% of the time, versus 11.9% for Strong IP. Generic re-elicitation averages 98.5% for Strong IP and 81.0% for CRT repair. At a predeclared layer-18 sensitivity condition, steering raises Strong IP to 46% and CRT repair to 4%, while patching produces small, non-selective changes. The results show why reproducibility studies should test suppression, replacement behavior, and restoration.