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

    Neuronpedia

    INDEX
    Explanations

    specific references to decisions, actions, and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ικα
    -0.15
    amel
    -0.15
    _FRAMEBUFFER
    -0.15
    ůž
    -0.15
    rita
    -0.15
    byn
    -0.14
    endon
    -0.14
    ovah
    -0.14
    readcr
    -0.14
    inton
    -0.13
    POSITIVE LOGITS
     or
    0.15
     qualche
    0.14
     somehow
    0.14
    uppies
    0.13
    лиÑĪком
    0.13
     unt
    0.13
    clusions
    0.13
    Ñīей
    0.13
     algún
    0.13
    verage
    0.13
    Act Density 0.486%

    No Known Activations