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

    Neuronpedia

    INDEX
    Explanations

    instances where something is physically held within a container

    oai_token-act-pair · gpt-3.5-turbo

    the term "contained" in various contexts related to inclusion or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrim
    -0.71
    urai
    -0.71
     partName
    -0.65
     Carney
    -0.64
    edes
    -0.64
    duc
    -0.62
    jac
    -0.62
     Scythe
    -0.61
    ammy
    -0.60
    STER
    -0.60
    POSITIVE LOGITS
    encies
    0.83
    iveness
    0.77
     therein
    0.75
    cakes
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.72
    cake
    0.71
    meat
    0.70
    ttes
    0.70
    prop
    0.69
    bars
    0.68
    Act Density 0.021%

    No Known Activations