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

    Neuronpedia

    INDEX
    Explanations

    words related to breathing activities like inhaling and exhaling

    oai_token-act-pair · gpt-3.5-turbo

    words related to health and respiratory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lunch
    -0.63
     Payton
    -0.63
     Fried
    -0.63
    fully
    -0.62
    llan
    -0.62
    actionDate
    -0.61
    Corp
    -0.60
     Canary
    -0.60
     Brach
    -0.59
     Marble
    -0.59
    POSITIVE LOGITS
    ospital
    0.95
     inh
    0.95
     exh
    0.92
    aled
    0.88
    avored
    0.87
    osp
    0.83
    ract
    0.79
    ogens
    0.77
     inhal
    0.76
    ressed
    0.75
    Act Density 0.022%

    No Known Activations