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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and their associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wie
    -0.17
    enas
    -0.14
    .ToolTip
    -0.14
    udio
    -0.14
    sdale
    -0.13
     moc
    -0.13
    OTA
    -0.13
     narrowly
    -0.13
    y
    -0.13
     margin
    -0.13
    POSITIVE LOGITS
    dings
    0.18
    745
    0.15
    ftware
    0.15
     ìľ
    0.14
    reece
    0.14
    วà¸ĩ
    0.14
    uitka
    0.14
    engers
    0.13
    tero
    0.13
    urement
    0.13
    Act Density 0.146%

    No Known Activations