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

    Neuronpedia

    INDEX
    Explanations

    terms related to privilege and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isol
    -0.17
    enga
    -0.15
    aling
    -0.15
    .AD
    -0.14
    jerne
    -0.14
    adesh
    -0.14
    دÙĪد
    -0.14
    istr
    -0.14
    addtogroup
    -0.14
    othermal
    -0.14
    POSITIVE LOGITS
    ously
    0.17
    bilt
    0.15
    dorf
    0.14
    .LayoutStyle
    0.14
    kh
    0.14
    ately
    0.14
    hardt
    0.14
    以åIJİ
    0.14
    طار
    0.14
    ä¹ĭä¸Ģ
    0.14
    Act Density 0.017%

    No Known Activations