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

    Neuronpedia

    INDEX
    Explanations

    references to the origins of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "origins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mun
    -0.73
    env
    -0.71
    train
    -0.70
    rooms
    -0.70
    room
    -0.69
    err
    -0.67
    uster
    -0.67
    roph
    -0.66
    urgical
    -0.66
    bus
    -0.66
    POSITIVE LOGITS
     anew
    0.78
     crowdfunding
    0.73
     fueling
    0.70
     Roots
    0.70
     thereof
    0.68
     Origins
    0.67
    waters
    0.66
     colonists
    0.66
     deriv
    0.65
     tracing
    0.64
    Act Density 0.022%

    No Known Activations