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

    Neuronpedia

    INDEX
    Explanations

    references to physical spaces, especially those related to commercial real estate

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of commercial and retail spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venge
    -0.79
    usted
    -0.72
    kai
    -0.70
    iamond
    -0.69
     VIDE
    -0.67
    endor
    -0.65
    inger
    -0.65
    tl
    -0.65
    ku
    -0.65
    ctive
    -0.64
    POSITIVE LOGITS
     spaces
    0.94
     space
    0.87
    bars
    0.80
     constraints
    0.79
     habitats
    0.79
     heater
    0.76
    conservancy
    0.76
     Layout
    0.76
     shuttle
    0.75
    kat
    0.75
    Act Density 0.022%

    No Known Activations