wang-yiwei Follow 
Stars
The entire MHDBDB stored in TEI files only
The Github repo for our survey paper: "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models"
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Sublime Text 3 的 jieba 分词库绑定，支持对中文更精确地选词、删词和按词移动光标
This is the official code for anchored bias of GPT2
Mechanistic analysis of Chain-of-Thought faithfulness using GPT-2 Small
Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University
Mech Interp Workshop at ICML 2024; NeurIPS 2024
code for ACL2024-main: BatchEval: Towards Human-like Text Evaluation
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Official inference framework for 1-bit LLMs
Offcial Repo of Paper "Eliminating Position Bias of Language Models: A Mechanistic Approach""
Make Zotero effective for us LaTeX holdouts
👩⚖️ Agent-as-a-Judge: The Magic for Open-Endedness
No fortress, purely open ground. OpenManus is Coming.
SciHRA-Detect is a parallel dataset of scientific abstracts in three forms — Human-Generated Text(HGT), AI-Revised Text(ART), and AI-Generated Text(AGT) — designed to support research in authorship…
[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks
D2X | Modern C++ Core Language Features - "A C++ tutorial project focused on practical"