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

    Neuronpedia

    INDEX
    Explanations

    mentions of the number of stories in buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of stories in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -1.02
    netflix
    -0.76
    wana
    -0.76
    icion
    -0.74
    iquid
    -0.71
    ogical
    -0.69
    apons
    -0.68
    brain
    -0.68
    ktop
    -0.66
    aceutical
    -0.66
    POSITIVE LOGITS
     balcony
    0.90
     apartment
    0.85
     buildings
    0.84
     tall
    0.83
    tall
    0.81
     balcon
    0.81
     dwellings
    0.80
     arc
    0.80
     rooftop
    0.74
     Corinth
    0.74
    Act Density 0.020%

    No Known Activations