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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or structural elements in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.85
    évaluateur
    -0.78
     $_-
    -0.67
    MUM
    -0.67
    ロウィン
    -0.66
    <unused47>
    -0.65
    <unused68>
    -0.65
    <unused74>
    -0.65
    <unused28>
    -0.65
    <unused16>
    -0.65
    POSITIVE LOGITS
     Constitución
    0.41
     sikkert
    0.40
     eneste
    0.36
     navideña
    0.35
     huella
    0.35
     interactiva
    0.34
     estekak
    0.33
     creciente
    0.33
     prí
    0.33
     préf
    0.33
    Act Density 0.001%

    No Known Activations