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

    Neuronpedia

    INDEX
    Explanations

    references to medical or legal terms in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.17
    asio
    -0.17
    erah
    -0.16
    iculo
    -0.16
    teborg
    -0.15
    akening
    -0.15
    amac
    -0.15
    ánu
    -0.15
    hton
    -0.15
     Rosenberg
    -0.15
    POSITIVE LOGITS
     to
    0.18
    gam
    0.15
    iet
    0.14
    -down
    0.14
     ll
    0.14
    in
    0.14
    à¹Ĩ
    0.13
     kepada
    0.13
     into
    0.13
    allet
    0.13
    Act Density 0.023%

    No Known Activations