NeuronpediaOpen Interpretability Platformhttps://www.neuronpedia.org/Google DeepMind has a new way to look inside an AI’s “mind”Autoencoders are letting us peer into the black box of artificial intelligence. They could help us create AI that is better understood, and more easily controlled.https://www.technologyreview.com/2024/11/14/1106871/google-deepmind-has-a-new-way-to-look-inside-an-ais-mind/
Seonglae ChoSeonglae ChoSeonglae ChoSeonglae Cho
