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

    Neuronpedia

    INDEX
    Explanations

    terms related to peak performance or high points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otton
    -0.15
     UT
    -0.14
     дов
    -0.14
    redo
    -0.13
    rac
    -0.13
    sip
    -0.13
    ην
    -0.13
    hn
    -0.13
    ario
    -0.13
    ajo
    -0.13
    POSITIVE LOGITS
     Lover
    0.15
    /Peak
    0.15
    ÅĽnie
    0.14
     Bik
    0.14
    æľŁ
    0.14
    levels
    0.14
     thá»ĭ
    0.14
    atform
    0.14
     levels
    0.13
     Perkins
    0.13
    Act Density 0.116%

    No Known Activations