feat: complete wikification of War Commander batch 1&2 and final grey dot cleanup
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
---
|
||||
id: CIRCUIT-001
|
||||
category: "[[10_Wiki/💡 Topics/AI]]"
|
||||
category: "10_Wiki/💡 Topics/AI"
|
||||
confidence_score: 1.0
|
||||
tags: [ai-interpretability, mechanistic-interpretability, neural-networks, circuits]
|
||||
last_reinforced: 2026-04-26
|
||||
@@ -24,6 +24,6 @@ last_reinforced: 2026-04-26
|
||||
- **정책 변화:** 모델의 안전성 검증(Alignment)을 위해 잠재적인 유해 논리 회로가 형성되었는지 감지하는 도구로 활용 비중 확대.
|
||||
|
||||
## 🔗 지식 연결 (Graph)
|
||||
- **Parent:** [[10_Wiki/💡 Topics/AI]]
|
||||
- **Related:** [[Mechanistic-Interpretability]], [[Neuron-Attribution]], [[Feature-Visualization]]
|
||||
- **Raw Source:** [[00_Raw/2026-04-20/Circuit Discovery.md]]
|
||||
- **Parent:** 10_Wiki/💡 Topics/AI
|
||||
- **Related:** Mechanistic-Interpretability, Neuron-Attribution, Feature-Visualization
|
||||
- **Raw Source:** 00_Raw/2026-04-20/Circuit Discovery.md
|
||||
|
||||
Reference in New Issue
Block a user