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

    Neuronpedia

    INDEX
    Explanations

    terms related to theoretical concepts and complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.15
     voks
    -0.15
    asti
    -0.15
    umer
    -0.14
    ument
    -0.14
    iej
    -0.14
    avn
    -0.14
    ENCHMARK
    -0.14
    ominated
    -0.14
    igin
    -0.14
    POSITIVE LOGITS
    ajar
    0.15
    üstü
    0.15
    /Register
    0.14
    iscard
    0.14
    ãĥ
    0.14
     upd
    0.14
    Truthy
    0.14
    otos
    0.14
    SENS
    0.13
    usu
    0.13
    Act Density 0.219%

    No Known Activations