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

    Neuronpedia

    INDEX
    Explanations

    references to interactions or relationships between multiple people

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffee
    -0.65
     Lans
    -0.61
     Hide
    -0.60
     1962
    -0.60
    ensibly
    -0.59
     Priest
    -0.59
    now
    -0.59
     1915
    -0.57
    uated
    -0.57
    ister
    -0.56
    POSITIVE LOGITS
    worldly
    1.65
    wise
    0.90
    quickShipAvailable
    0.81
    swer
    0.81
     aspects
    0.73
     major
    0.69
     installments
    0.69
     side
    0.68
    IES
    0.66
    hesis
    0.66
    Act Density 0.083%

    No Known Activations