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

    Neuronpedia

    INDEX
    Explanations

    phrases directed towards the reader or listener

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    infeld
    -0.17
    UAGE
    -0.14
    raries
    -0.14
    Å¡k
    -0.14
    áš
    -0.14
    omik
    -0.14
     cours
    -0.13
    ral
    -0.13
    .debian
    -0.13
     Rap
    -0.13
    POSITIVE LOGITS
     âĨij
    0.15
    onces
    0.15
     bdsm
    0.14
    ones
    0.14
    ulado
    0.13
    NAV
    0.13
    beb
    0.13
     Vale
    0.13
     Boom
    0.13
    637
    0.13
    Act Density 0.260%

    No Known Activations