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

    Neuronpedia

    INDEX
    Explanations

    terms related to superiority and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ess
    -0.17
    ses
    -0.17
    اÙģت
    -0.16
    æļ®
    -0.16
    alty
    -0.16
    athon
    -0.15
    üz
    -0.15
    bette
    -0.15
    room
    -0.15
    (es
    -0.15
    POSITIVE LOGITS
    atively
    0.19
    arily
    0.18
    ìłģìľ¼ë¡ľ
    0.16
    vably
    0.16
    inary
    0.16
    /sub
    0.16
    most
    0.15
    alse
    0.15
    /current
    0.15
    istically
    0.15
    Act Density 0.040%

    No Known Activations