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

    Neuronpedia

    INDEX
    Explanations

    references to "behind the scenes" or similar phrases that imply hidden or less visible aspects of a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    伦
    -0.14
    duk
    -0.14
     inferior
    -0.14
    cairo
    -0.14
    ortic
    -0.14
    iband
    -0.14
    apy
    -0.14
     Nach
    -0.14
    .bad
    -0.13
     deferred
    -0.13
    POSITIVE LOGITS
    ninger
    0.15
    olina
    0.15
    ADO
    0.14
    Drawer
    0.14
    dma
    0.14
    OCUS
    0.14
    stract
    0.14
    ãĥ³ãĥĦ
    0.14
    iosk
    0.14
     thá»Ŀ
    0.14
    Act Density 0.011%

    No Known Activations