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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology related to matrices and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.62
     endwhile
    -0.52
     getItemCount
    -0.50
     unknownFields
    -0.48
    WriteLiteral
    -0.46
    تفصیلات
    -0.45
    rxjs
    -0.45
     onOptions
    -0.44
    السكان
    -0.44
     Dostupné
    -0.43
    POSITIVE LOGITS
     matrix
    0.69
     матри
    0.65
    Matrix
    0.63
     Matrix
    0.62
    matrix
    0.59
     matrices
    0.58
     MATRIX
    0.57
    矩阵
    0.54
     matri
    0.53
    matrices
    0.52
    Act Density 0.834%

    No Known Activations