Extended Data Fig. 2: Figure S2. Comparing GPT-2 predictions and human predictions. | Nature Neuroscience

Extended Data Fig. 2: Figure S2. Comparing GPT-2 predictions and human predictions.

From: Shared computational principles for language processing in humans and deep language models

Extended Data Fig. 2: Figure S2. Comparing GPT-2 predictions and human predictions.

Coloring the scatter plot according to GPT-2/human accuracy. GPT-2 and humans jointly predicted correctly 27.6% of the words (green). GPT-2 and humans jointly predicted incorrectly and disagreed on the next word for 48.8% of the words (red). GPT-2 and humans jointly predicted incorrectly and agreed on the next word for 5.9% of the words (black) 9.2% of the words humans predicted correctly were not correctly predicted by GPT-2 (blue). 8.4% of the words correctly predicted by GPT-2 were not correctly predicted by humans.

Back to article page