Skip to main content
Back to catalog

GPT-NeoX / Pythia

1 glitch tokens

These tokens have been publicly documented on this model or model family. Inclusion does not mean that every version still shows the same behavior.

␣NdEx

Fragments of legal/PDF text (“index”, “AFFIRMED”, “NEGLIGENCE”, likely from court-document dumps) that GPT-NeoX/Pythia training data barely contained. Same family: ` FFIRMED`, ` GLIGENCE`, ` affidav`, ` taxp`.
GPT-NeoX / PythiaUnder-trained