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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey superiority or quality related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sat
    -0.15
    ede
    -0.15
    deen
    -0.15
    stants
    -0.15
     صاد
    -0.14
    lian
    -0.14
    _defaults
    -0.14
    ÌĢ
    -0.14
    arga
    -0.13
    ryn
    -0.13
    POSITIVE LOGITS
     svens
    0.15
    mare
    0.15
    irut
    0.14
    kid
    0.14
    /latest
    0.14
    _PO
    0.14
     ç³
    0.14
    /power
    0.14
    OSE
    0.13
    ofilm
    0.13
    Act Density 0.047%

    No Known Activations