Popular repositories Loading

1. Bio-focussed-NLP-explainability Bio-focussed-NLP-explainability Public

   Investigation into ML explainability/interpretability techniques, analysing the behaviour of ML models trained to predict whether a medical abstract is or is not related to pathogens.

   Jupyter Notebook

2. LLM-model-comparison LLM-model-comparison Public

   LLM comparison notebook evaluating GPT-4.1, GPT-4.1 Mini, Llama 3.1 8B, and Qwen 2.5 7B on structured AI lab assessments (AI safety risk + ROI). Includes scoring rubric, analysis pipeline, and inte…

   Jupyter Notebook

3. three-headlines-and-a-lie three-headlines-and-a-lie Public

   Predicting which headline is fake out of a choice of three real headlines and one fake headline using different ML models. Final output of an app where users can test their performance against the …

   Jupyter Notebook

4. mini-alignment-eval mini-alignment-eval Public

   Python

5. alex alex Public

   Forked from ed-donner/alex

   Python