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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating where people live

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individuals' living situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptic
    -0.76
    elight
    -0.75
    vernment
    -0.72
    iasis
    -0.69
    sonian
    -0.68
    xual
    -0.67
    oug
    -0.67
    ause
    -0.66
    reg
    -0.65
    emonic
    -0.63
    POSITIVE LOGITS
     upstairs
    0.95
     paycheck
    0.93
     downstairs
    0.90
     vic
    0.89
    chool
    0.88
     abroad
    0.82
    stead
    0.81
     Rent
    0.75
    house
    0.75
    stein
    0.73
    Act Density 0.045%

    No Known Activations