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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate emphasis or significant change in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.16
    presso
    -0.16
    hol
    -0.14
    ennes
    -0.14
    lope
    -0.14
     Elis
    -0.14
     Margin
    -0.14
    oro
    -0.14
     determinant
    -0.14
     Bundle
    -0.14
    POSITIVE LOGITS
    oker
    0.18
    ém
    0.16
    ITO
    0.15
    empl
    0.14
    дÑı
    0.13
    ione
    0.13
    ÑĤоÑĢа
    0.13
    acer
    0.13
    FieldType
    0.13
    urdy
    0.13
    Act Density 0.039%

    No Known Activations