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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical cleaning actions, especially involving hands and face

    oai_token-act-pair · gpt-3.5-turbo

    mentions of washing or cleaning activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.73
    SPONSORED
    -0.73
    trak
    -0.69
    supported
    -0.68
    argument
    -0.68
    ItemThumbnailImage
    -0.66
    ĺħ
    -0.65
     bargaining
    -0.62
    Trend
    -0.61
     Mobility
    -0.61
    POSITIVE LOGITS
     floors
    1.03
     dishes
    1.00
     toilets
    1.00
     linen
    0.98
     thoroughly
    0.94
     wounds
    0.92
     stains
    0.91
     slate
    0.90
     surfaces
    0.90
     dirty
    0.89
    Act Density 0.240%

    No Known Activations