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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to people and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.69
     typelib
    -0.61
     ProtoMessage
    -0.61
    CppMethod
    -0.60
    HideFlags
    -0.60
    ValueStyle
    -0.60
    XmlAccessorType
    -0.57
    ⤹
    -0.56
    OfWork
    -0.55
    =?";
    -0.55
    POSITIVE LOGITS
    ha
    0.94
    wa
    0.91
    HA
    0.75
     Wa
    0.71
    ya
    0.71
    Wa
    0.70
    WA
    0.66
    Ha
    0.62
     Ha
    0.61
    za
    0.57
    Act Density 2.155%

    No Known Activations