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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of a specific character or symbol, indicating a pattern or structure in the document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueGeneration
    -0.60
     ?>/
    -0.60
    rrggbb
    -0.56
     verlang
    -0.54
    izable
    -0.53
     Anm
    -0.52
    avaş
    -0.51
    piecze
    -0.51
    COMPARE
    -0.50
    док
    -0.49
    POSITIVE LOGITS
    setupUi
    0.62
    Jeografia
    0.61
    Geplaatst
    0.60
    <bos>
    0.58
    EDEFAULT
    0.57
    principalTable
    0.56
    AutoScale
    0.54
    TextEditing
    0.54
    asticity
    0.52
    "><!--
    0.52
    Act Density 0.007%

    No Known Activations