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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and properties related to matrices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    المناصب
    -0.54
    SPATH
    -0.50
     moderation
    -0.46
     MODER
    -0.44
     Mahomet
    -0.43
    makeText
    -0.42
     esterni
    -0.42
     insuffisamment
    -0.42
     Waray
    -0.42
    НИК
    -0.41
    POSITIVE LOGITS
     matrix
    1.06
     matrices
    1.00
    matrix
    0.95
     Matrix
    0.91
    Matrix
    0.89
     Matrices
    0.87
    矩阵
    0.87
     MATRIX
    0.86
     матри
    0.83
    matrices
    0.82
    Act Density 1.147%

    No Known Activations