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

    Neuronpedia

    INDEX
    Explanations

    words related to leaving or departing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.76
    DeleteBehavior
    -0.69
     kiin
    -0.64
    ItemSelected
    -0.62
    expandindo
    -0.59
    élimin
    -0.59
     Rptr
    -0.58
     cappuccio
    -0.57
    wenye
    -0.56
    berdayakan
    -0.54
    POSITIVE LOGITS
    Depart
    0.80
     departure
    0.77
     departures
    0.77
     Departure
    0.76
     departs
    0.76
     depart
    0.73
    departure
    0.71
    depart
    0.71
     Depart
    0.69
     departing
    0.68
    Act Density 0.014%

    No Known Activations