Glossary
Concepts and terminology.
Short, linkable definitions of the ideas behind abliteration, refusal editing, activation steering, and policy-controlled LLM APIs.
Orthogonalization
How orthogonalization removes unwanted directions in activation space.
Refusal vector
Definition of refusal vectors in LLMs and how they power abliteration.
Refusal vector ablation
How refusal vector ablation removes refusal behavior while preserving core model capability.
Residual stream
Definition of the transformer residual stream and why it matters for activation editing.
Looking for integration guides?
The glossary defines terms. The developer docs show you how to ship with the API, Policy Gateway, and audit-log exports.
Developer docs