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

    Neuronpedia

    INDEX
    Explanations

    verbs related to leaving or departing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "depart" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acca
    -0.74
    essee
    -0.72
    iop
    -0.71
    izable
    -0.67
    Sol
    -0.64
    flix
    -0.62
    kefeller
    -0.61
    ibur
    -0.61
    andan
    -0.61
    thouse
    -0.60
    POSITIVE LOGITS
     undone
    0.76
     departure
    0.71
    wich
    0.70
     Leaves
    0.69
    azard
    0.68
    ï¸
    0.65
     departures
    0.65
     anytime
    0.65
    uary
    0.63
    untled
    0.62
    Act Density 0.024%

    No Known Activations