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

    Neuronpedia

    INDEX
    Explanations

    references to news sources or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icap
    -0.15
     ama
    -0.14
    irector
    -0.14
    ulture
    -0.14
    gaard
    -0.14
     king
    -0.14
    assin
    -0.14
     mec
    -0.14
     Laden
    -0.14
    upert
    -0.14
    POSITIVE LOGITS
     lim
    0.17
    efa
    0.14
    Managed
    0.14
    IFORM
    0.14
    MOVED
    0.13
    vey
    0.13
    วม
    0.13
    Reusable
    0.13
    acher
    0.12
    ÐŀÑģнов
    0.12
    Act Density 0.008%

    No Known Activations