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

    Neuronpedia

    INDEX
    Explanations

    references to the interiors of physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "interior."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.79
    fortune
    -0.72
    thood
    -0.71
    arov
    -0.68
    Ox
    -0.67
    yip
    -0.67
    ansky
    -0.65
    KING
    -0.64
    veyard
    -0.63
    imaru
    -0.62
    POSITIVE LOGITS
     interior
    1.21
    door
    0.94
     ministry
    0.93
     decoration
    0.90
     seams
    0.87
     renovation
    0.85
     renovations
    0.83
     Interior
    0.82
     decor
    0.80
     entrances
    0.79
    Act Density 0.005%

    No Known Activations