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

    Neuronpedia

    INDEX
    Explanations

    words related to real estate or buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to residential properties and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -1.01
    ĸļ
    -0.84
    erity
    -0.84
    lda
    -0.82
    imoto
    -0.75
    arak
    -0.75
    urat
    -0.72
    xtap
    -0.72
    gerald
    -0.72
    bring
    -0.70
    POSITIVE LOGITS
     dwellings
    1.02
    ization
    0.88
     buildings
    0.87
    ized
    0.86
     occupancy
    0.86
     tenancy
    0.86
     residential
    0.85
    ised
    0.82
    izes
    0.82
     residences
    0.82
    Act Density 0.015%

    No Known Activations