Extended Data Fig. 6: Object dimensions (57-66) illustrating their interpretability for LLM (left) and MLLM (right). | Nature Machine Intelligence

Extended Data Fig. 6: Object dimensions (57-66) illustrating their interpretability for LLM (left) and MLLM (right).

From: Human-like object concept representations emerge naturally in multimodal large language models

Extended Data Fig. 6: Object dimensions (57-66) illustrating their interpretability for LLM (left) and MLLM (right).The alternative text for this image may have been generated using AI.

Related to Fig. 4. Each dimension is illustrated with the top 6 images with the highest weights along this dimension. All images were replaced with similar images from Pixabay and Pexels under a Creative Commons license CC0.

Back to article page