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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of phrases containing the word "of" and similar contextual words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QMetaType
    -0.66
    matism
    -0.65
     ADM
    -0.62
     acost
    -0.60
    XmlAccessType
    -0.60
    ASN
    -0.59
    udara
    -0.59
     PLA
    -0.59
    таратура
    -0.57
     dran
    -0.57
    POSITIVE LOGITS
    anjutan
    0.80
    MathML
    0.78
     these
    0.71
    ReusableCell
    0.69
     Quinn
    0.65
    Quinn
    0.64
    LogFactory
    0.63
     toilettes
    0.63
    zegor
    0.63
    archiviato
    0.63
    Act Density 0.130%

    No Known Activations