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

    Neuronpedia

    INDEX
    Explanations

    mentions of places or objects related to houses, such as "garage" and "basement."

    oai_token-act-pair · gpt-3.5-turbo

    references to garages and basements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andum
    -0.99
    uality
    -0.93
    utical
    -0.83
    lda
    -0.74
    tics
    -0.71
    irection
    -0.70
    atform
    -0.69
    idate
    -0.69
    utics
    -0.69
    thood
    -0.68
    POSITIVE LOGITS
     attic
    1.09
     door
    1.03
     basement
    0.95
    door
    0.93
     closet
    0.92
     doors
    0.92
     bedroom
    0.91
     renovation
    0.90
     fireplace
    0.90
     Door
    0.89
    Act Density 0.062%

    No Known Activations