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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "matrix," particularly in various contexts related to mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    сылкі
    -0.67
     répé
    -0.58
     coupable
    -0.58
     blessés
    -0.56
     drôle
    -0.55
     soigne
    -0.55
    icionar
    -0.54
     secondaires
    -0.52
     Inscrivez
    -0.51
    صیل
    -0.51
    POSITIVE LOGITS
     matrix
    3.41
     Matrix
    2.94
    matrix
    2.84
     matrices
    2.82
     MATRIX
    2.58
    Matrix
    2.53
     Matrices
    2.38
    MATRIX
    2.19
    matrices
    2.17
    矩阵
    2.12
    Act Density 0.030%

    No Known Activations