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

    Neuronpedia

    INDEX
    Explanations

    distinctive patterns or classifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _BUFF
    -0.15
    eldon
    -0.15
     Bever
    -0.14
    essen
    -0.14
    zá
    -0.14
    engin
    -0.14
    ertest
    -0.13
    .HtmlControls
    -0.13
    à¸Ńà¸Ń
    -0.13
    åŁ
    -0.13
    POSITIVE LOGITS
    af
    0.34
    ab
    0.34
    apro
    0.34
    ap
    0.33
    apr
    0.32
    amed
    0.32
    ase
    0.30
    aj
    0.30
    aw
    0.29
     ab
    0.28
    Act Density 0.222%

    No Known Activations