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

    Neuronpedia

    INDEX
    Explanations

    terms related to different types of real estate properties, especially residential properties

    oai_token-act-pair · gpt-3.5-turbo

    references to residential properties and areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -1.06
    erity
    -0.83
    urat
    -0.79
    nir
    -0.79
    imoto
    -0.76
    hered
    -0.73
    arak
    -0.72
    generic
    -0.72
    gans
    -0.71
    xtap
    -0.70
    POSITIVE LOGITS
     dwellings
    0.99
    ization
    0.95
     occupancy
    0.95
    ized
    0.93
    izes
    0.90
     tenancy
    0.90
     buildings
    0.87
     halls
    0.84
     burglary
    0.84
    ised
    0.83
    Act Density 0.026%

    No Known Activations