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

    Neuronpedia

    INDEX
    Explanations

    words associated with positive attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aj
    -0.16
    irsch
    -0.16
    ongo
    -0.14
    ajs
    -0.14
    atos
    -0.13
    лоÑĢ
    -0.13
    isto
    -0.13
    uros
    -0.13
    edral
    -0.13
    vang
    -0.13
    POSITIVE LOGITS
    edly
    0.18
    RectTransform
    0.17
    léd
    0.15
    odont
    0.15
    esome
    0.15
    ultip
    0.14
    ανά
    0.14
    ober
    0.14
    heit
    0.14
    ÏĤ
    0.14
    Act Density 0.109%

    No Known Activations