Exploring the shift cipher data from our paper “Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve”Tips and tricks for running experiments on Amazon Mechanical TurkSummary and demo for our paper “Universal linguistic inductive biases via meta-learning”Detailed results for our paper “Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks”Summary and demo for our paper “RNNs implicitly implement Tensor Product Representations”
