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

    Neuronpedia

    INDEX
    Explanations

    personal names of notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent individuals or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inspection
    -0.78
     antioxid
    -0.72
     warranty
    -0.70
    ordinate
    -0.69
    mination
    -0.68
     opio
    -0.67
     reproduction
    -0.67
     glim
    -0.67
     qualitative
    -0.65
     issu
    -0.62
    POSITIVE LOGITS
     Jr
    1.10
    enegger
    1.00
    Jr
    0.95
     Sr
    0.92
     assassinated
    0.85
     famously
    0.82
     Himself
    0.79
     himself
    0.76
    mania
    0.76
     Billion
    0.72
    Act Density 0.503%

    No Known Activations