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

    Neuronpedia

    INDEX
    Explanations

    truth values or logical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >");
    -0.65
    >');
    -0.60
    ')):
    -0.57
    )');
    -0.56
    '}}>
    -0.55
    ()));
    -0.55
    ')),
    -0.55
    "]);
    -0.54
    "])){
    -0.53
    >");
    -0.53
    POSITIVE LOGITS
     onOptions
    0.70
    numerusform
    0.62
    maline
    0.62
    ſelf
    0.59
    Portale
    0.57
     AssemblyCompany
    0.56
     فريبيس
    0.56
     NDEBUG
    0.56
    culin
    0.55
     Houſe
    0.55
    Act Density 0.731%

    No Known Activations