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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.61
    <b>
    -0.58
     "
    -0.55
    <u>
    -0.55
    </blockquote>
    -0.52
    <strong>
    -0.51
     ]
    -0.51
     pener
    -0.50
    keli
    -0.48
    iti
    -0.47
    POSITIVE LOGITS
    ftagPool
    1.01
    endphp
    1.00
    存于互联网档案馆
    0.93
     noqa
    0.91
     مشين
    0.83
    Personensuche
    0.81
    OGND
    0.80
    SequentialGroup
    0.80
    SharedCtor
    0.79
     RZ
    0.78
    Act Density 0.531%

    No Known Activations