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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and planning

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    former
    -0.69
    roud
    -0.66
    ĸļ
    -0.66
    avid
    -0.65
    creator
    -0.64
    uin
    -0.64
    ciating
    -0.62
    uments
    -0.62
    verified
    -0.61
     Founder
    -0.60
    POSITIVE LOGITS
     should
    0.99
     constitutes
    0.93
     appropriate
    0.93
     priorities
    0.89
     best
    0.86
     qualifies
    0.86
     ought
    0.85
    Should
    0.82
     allowable
    0.82
    should
    0.82
    Act Density 0.291%

    No Known Activations