activation steeringChanging a model's behavior by nudging its internal activations directly at runtime — no retraining, no prompt changes.Full definition → changes model behavior or personality at inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → time with no training data or fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → compute, an option when prompts are insufficient.
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
activation steering — Changing a model's behavior by nudging its internal activations directly at runtime — no retraining, no prompt changes.
