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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of the interior of objects or spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to "interior" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortune
    -0.85
    thood
    -0.79
    tle
    -0.77
    SHIP
    -0.72
    ansky
    -0.72
    Ox
    -0.72
    arov
    -0.71
    fleet
    -0.69
    KING
    -0.68
    nir
    -0.67
    POSITIVE LOGITS
     interior
    1.06
     decoration
    0.90
     ministry
    0.90
    door
    0.83
     decor
    0.83
     perimeter
    0.82
     door
    0.82
     workings
    0.80
     seams
    0.79
     entrances
    0.77
    Act Density 0.007%

    No Known Activations