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

    Neuronpedia

    INDEX
    Explanations

    mentions of living spaces, particularly apartments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of apartments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.94
    vous
    -0.86
    ¶ħ
    -0.82
    nir
    -0.78
    à¥
    -0.77
    ²¾
    -0.77
    xon
    -0.76
    xtap
    -0.74
    ा
    -0.73
    terday
    -0.72
    POSITIVE LOGITS
     apartment
    1.08
     balcony
    1.04
     complexes
    1.02
     apartments
    1.01
     balcon
    0.91
     dwellings
    0.89
     buildings
    0.89
     furniture
    0.89
     rentals
    0.84
     Dwell
    0.80
    Act Density 0.014%

    No Known Activations