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

    Neuronpedia

    INDEX
    Explanations

    negative powers in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    gridx
    -0.71
    awaiter
    -0.66
    ism
    -0.65
     preghiera
    -0.63
    ništvo
    -0.61
     متعلقه
    -0.61
    es
    -0.60
     marito
    -0.60
     cub
    -0.58
    rsiniz
    -0.58
    POSITIVE LOGITS
    HtmlAttribute
    0.93
    mtable
    0.72
    inafter
    0.72
    atimes
    0.72
    apeake
    0.71
    indrome
    0.67
     moly
    0.66
     QtWidgets
    0.66
    SequentialGroup
    0.65
     Tamp
    0.65
    Act Density 0.013%

    No Known Activations