Therefore I am. I Think

1. 1Investigate pre-generation activations in large language models to understand decision-making processes
2. 2Use linear probes to decode tool-calling decisions from these activations
3. 3Analyze the timing of decision-making in relation to reasoning chain generation
4. 4Evaluate the implications of early-encoded decisions on model transparency and explainability

AI researchers and engineers can benefit from understanding how language models make decisions, which can inform the development of more transparent and explainable AI systems

💡 Detectable, early-encoded decisions shape chain-of-thought in reasoning models

💡 Large language models make decisions before generating reasoning chains!