Emerging techniques in computer science make it possible to "brain scan" large language models (LLMs), identify the plain-English concepts that guide their reasoning, and steer them while holding other factors constant. We show that this approach can map LLM-generated economic forecasts to concepts such as sentiment, technical analysis, and timing, and compute their relative importance without reducing performance. We also show that models can be steered to be more or less risk-averse, optimistic, or pessimistic, which allows researchers to correct or simulate biases. The method is transparent, lightweight, and replicable for empirical research in the social sciences.

翻译：计算机科学的新兴技术使得对大型语言模型进行"脑扫描"成为可能，即识别指导其推理的纯英文概念，并在保持其他因素不变的情况下引导其行为。我们证明，该方法能够将LLM生成的经济预测映射至诸如市场情绪、技术分析和时机选择等概念，并在不降低性能的前提下计算这些概念的相对重要性。我们还证明，可以通过引导使模型表现出不同程度的风险规避、乐观或悲观倾向，从而使研究人员能够修正或模拟认知偏差。该方法具有透明性、轻量化及可复现的特点，适用于社会科学领域的实证研究。