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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is unable to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating lack of ability or capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.76
    soType
    -0.75
    oak
    -0.74
    soDeliveryDate
    -0.70
    RAFT
    -0.69
     Tradition
    -0.69
    deals
    -0.66
    cour
    -0.64
    Benz
    -0.63
    ocard
    -0.63
    POSITIVE LOGITS
     compe
    0.89
    ioned
    0.86
    icably
    0.77
     necessarily
    0.76
     adequately
    0.76
     incap
    0.74
    xes
    0.74
     incapac
    0.69
     inval
    0.69
     burd
    0.68
    Act Density 0.022%

    No Known Activations