Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unnatural
    -0.07
    �
    -0.07
     Morning
    -0.06
     yourself
    -0.06
    ted
    -0.06
    든지
    -0.06
    _lineno
    -0.06
     login
    -0.06
     каз
    -0.06
     hos
    -0.06
    POSITIVE LOGITS
    acements
    0.08
    ⇛
    0.08
    퀘
    0.07
    鄞
    0.07
     создания
    0.07
    🌇
    0.07
    anship
    0.07
    养殖场
    0.07
    luent
    0.07
     diner
    0.07
    Act Density 0.127%

    No Known Activations