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

    Neuronpedia

    INDEX
    Explanations

    references to interior spaces or designs

    oai_token-act-pair · gpt-3.5-turbo

    references to interior spaces or interior design elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortune
    -0.86
    arov
    -0.84
    andum
    -0.81
    thood
    -0.81
    nir
    -0.80
    unin
    -0.80
    urai
    -0.75
    astically
    -0.74
    eday
    -0.74
    tle
    -0.72
    POSITIVE LOGITS
     decoration
    0.92
     ministry
    0.88
     interior
    0.85
     workings
    0.84
    most
    0.81
     Designer
    0.81
     renovations
    0.81
     decor
    0.80
    ITY
    0.76
     customization
    0.75
    Act Density 0.018%

    No Known Activations