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

    Neuronpedia

    INDEX
    Explanations

    specific structural elements or commands in programming and mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.75
     and
    -0.60
     (
    -0.57
    .
    -0.56
    ;
    -0.50
    ↵↵
    -0.49
    :
    -0.46
    และ
    -0.46
    ışık
    -0.45
     absolutely
    -0.45
    POSITIVE LOGITS
    <bos>
    3.16
     Савезне
    1.48
     Мексичка
    1.23
     Paglinawan
    1.21
     виправивши
    1.20
    ’
    1.16
     للمعارف
    1.14
    хьтан
    1.11
    '
    1.10
     disambiguazione
    1.10
    Act Density 0.785%

    No Known Activations