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

    Neuronpedia

    INDEX
    Explanations

    keywords related to observing or interacting with others in a specific physical space

    oai_token-act-pair · gpt-3.5-turbo

    mentions of passersby and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cay
    -0.65
     marrow
    -0.65
    undo
    -0.63
    ested
    -0.61
    eat
    -0.61
    arus
    -0.61
    ripp
    -0.61
     Milk
    -0.60
     Lod
    -0.60
     Netherlands
    -0.60
    POSITIVE LOGITS
    by
    0.92
    ages
    0.86
    iper
    0.81
    lihood
    0.81
     passer
    0.81
    ky
    0.75
    age
    0.73
     wip
    0.73
    iqueness
    0.70
    atures
    0.70
    Act Density 0.046%

    No Known Activations