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

    Neuronpedia

    INDEX
    Explanations

    words related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meiden
    -0.15
     nackte
    -0.14
    cedes
    -0.14
     Jak
    -0.14
    ker
    -0.13
    ê·¼
    -0.13
    pheres
    -0.13
    cores
    -0.13
    201
    -0.13
     Levy
    -0.13
    POSITIVE LOGITS
    okable
    0.16
    udu
    0.15
    lech
    0.15
    лаг
    0.15
     Strom
    0.14
    uco
    0.14
     Tep
    0.14
    uish
    0.14
    orthand
    0.14
    lycer
    0.13
    Act Density 0.014%

    No Known Activations