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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating surprise or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PeEnEo
    -0.62
     akka
    -0.55
    <bos>
    -0.54
    thâu
    -0.53
     OFDb
    -0.52
     hoppas
    -0.51
     EconPapers
    -0.49
    wery
    -0.49
    Kontrola
    -0.48
    anderen
    -0.48
    POSITIVE LOGITS
     unsur
    0.73
    الدراسه
    0.58
     defStyle
    0.58
     inevitable
    0.57
     inevitably
    0.56
    Risultati
    0.55
    vodu
    0.53
    contentLoaded
    0.52
    anthrene
    0.52
    "}";
    0.51
    Act Density 0.234%

    No Known Activations