Steering the CensorShip Sleeping Agents 2 DeepSeek-R1 Censorship Steering 🐳 2 Generate text with adjustable censorship control Running on Zero Agents 8 Refusal Censorship Steering 🦙 8 Generate text with adjustable censorship control Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Paper • 2504.17130 • Published Apr 23, 2025 • 1
Sleeping Agents 2 DeepSeek-R1 Censorship Steering 🐳 2 Generate text with adjustable censorship control
Running on Zero Agents 8 Refusal Censorship Steering 🦙 8 Generate text with adjustable censorship control
Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Paper • 2504.17130 • Published Apr 23, 2025 • 1
Steering the CensorShip Sleeping Agents 2 DeepSeek-R1 Censorship Steering 🐳 2 Generate text with adjustable censorship control Running on Zero Agents 8 Refusal Censorship Steering 🦙 8 Generate text with adjustable censorship control Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Paper • 2504.17130 • Published Apr 23, 2025 • 1
Sleeping Agents 2 DeepSeek-R1 Censorship Steering 🐳 2 Generate text with adjustable censorship control
Running on Zero Agents 8 Refusal Censorship Steering 🦙 8 Generate text with adjustable censorship control
Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control Paper • 2504.17130 • Published Apr 23, 2025 • 1
