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

    Neuronpedia

    INDEX
    Explanations

    words that indicate significance or quantify importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stit
    -0.15
    rary
    -0.15
    ackbar
    -0.14
    ä¸
    -0.14
    DMIN
    -0.13
     itk
    -0.13
    chten
    -0.13
    regunta
    -0.13
    /lg
    -0.13
    ften
    -0.13
    POSITIVE LOGITS
    untas
    0.16
    edor
    0.15
     pand
    0.15
    remium
    0.14
     Pon
    0.14
     Pandora
    0.14
    vá
    0.14
     sine
    0.13
     stump
    0.13
    endir
    0.13
    Act Density 0.003%

    No Known Activations