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

    Neuronpedia

    INDEX
    Explanations

    references to interior design elements

    oai_token-act-pair · gpt-3.5-turbo

    references to interior spaces or designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unin
    -0.89
    fortune
    -0.86
    nir
    -0.84
    arov
    -0.83
    urai
    -0.81
    astically
    -0.80
    tle
    -0.78
    veyard
    -0.77
    eday
    -0.76
    thood
    -0.76
    POSITIVE LOGITS
     decoration
    1.01
     ministry
    0.96
     interior
    0.93
     decor
    0.93
     renovations
    0.89
     workings
    0.84
     renovation
    0.82
    most
    0.81
     decorations
    0.81
     Designer
    0.79
    Act Density 0.022%

    No Known Activations