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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or potential

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <strong>
    -0.66
     I
    -0.64
    ot
    -0.58
     opportunities
    -0.58
     minat
    -0.58
    ms
    -0.57
     available
    -0.56
     Bezug
    -0.56
    I
    -0.56
    доступ
    -0.55
    POSITIVE LOGITS
     صوتيه
    1.03
    extAlignment
    1.02
     Cæsar
    0.98
    fromCharCode
    0.98
    TintMode
    0.97
     AtomicInteger
    0.96
    fillType
    0.94
     Monks
    0.94
    PMailer
    0.94
     Roskov
    0.91
    Act Density 0.004%

    No Known Activations