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

    Neuronpedia

    INDEX
    Explanations

    instances of people standing or waiting in lines in various settings

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the phrase "in" followed by a number of references to "sitting" or "standing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.71
    cia
    -0.67
    ulet
    -0.65
    eni
    -0.65
    gans
    -0.64
    ¥
    -0.63
     selves
    -0.62
    gem
    -0.61
    ŀ
    -0.61
    etheless
    -0.60
    POSITIVE LOGITS
     front
    1.17
     limbo
    0.99
     lieu
    0.97
     obscurity
    0.97
     ambush
    0.94
     isolation
    0.93
     awe
    0.92
     anticipation
    0.89
     chairs
    0.88
     queues
    0.88
    Act Density 0.129%

    No Known Activations