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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     difficulty
    -0.09
     interest
    -0.08
    ié
    -0.07
    .null
    -0.07
    ء
    -0.07
    趣
    -0.07
    缘
    -0.07
    樊
    -0.07
    壑
    -0.07
    岖
    -0.07
    POSITIVE LOGITS
     Freed
    0.07
     breeding
    0.07
     Terminator
    0.07
     AK
    0.07
     admissions
    0.06
    acists
    0.06
    黑客
    0.06
     compilation
    0.06
     metabolism
    0.06
     ;)↵↵
    0.06
    Act Density 0.013%

    No Known Activations