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

    Neuronpedia

    INDEX
    Explanations

    places or areas that are inhabited or populated by people or groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to population density and habitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enic
    -0.85
    heet
    -0.81
    udic
    -0.80
    stroke
    -0.78
    iem
    -0.78
    ripp
    -0.78
    nir
    -0.76
    hedral
    -0.76
    ibur
    -0.76
    aina
    -0.75
    POSITIVE LOGITS
     inhabited
    0.89
     dwellings
    0.79
     dwelling
    0.78
     inhab
    0.73
     occupied
    0.71
     inhabitants
    0.69
     habitable
    0.69
     dwell
    0.69
     villages
    0.69
     Packs
    0.69
    Act Density 0.032%

    No Known Activations