Bhargav, S., & Zhu, Z. (2025). Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts.
Cita Chicago Style (17a ed.)Bhargav, Samaksh, y Zining Zhu. Feature-Guided SAE Steering for Refusal-Rate Control Using Contrasting Prompts. 2025.
Cita MLA (9a ed.)Bhargav, Samaksh, y Zining Zhu. Feature-Guided SAE Steering for Refusal-Rate Control Using Contrasting Prompts. 2025.
Precaución: Estas citas no son 100% exactas.