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

    Neuronpedia

    INDEX
    Explanations

    references to living spaces, particularly dwellings or inhabitants

    oai_token-act-pair · gpt-3.5-turbo

    references to people living in or associated with dwellings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     athlet
    -0.75
    AAF
    -0.72
    Downloadha
    -0.71
    xon
    -0.68
    channelAvailability
    -0.68
    ripp
    -0.64
    avez
    -0.64
    alky
    -0.62
    enic
    -0.62
    xxxxxxxx
    -0.61
    POSITIVE LOGITS
     dwell
    1.15
     dwelling
    1.09
     Dwell
    1.04
    lords
    0.98
    ers
    0.95
    erers
    0.89
    erness
    0.88
    rite
    0.81
    ants
    0.77
    reth
    0.77
    Act Density 0.008%

    No Known Activations