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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific variables or parameters within mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.81
     فريبيس
    -0.79
     Профиль
    -0.77
    出版年
    -0.77
     ARXIV
    -0.77
    kloped
    -0.76
    "}>
    -0.76
    Попис
    -0.76
    Controllo
    -0.74
     Мексичка
    -0.73
    POSITIVE LOGITS
     F
    1.38
     C
    1.35
     B
    1.35
    F
    1.20
     R
    1.18
     D
    1.15
     A
    1.13
    B
    1.13
     E
    1.12
    C
    1.10
    Act Density 0.883%

    No Known Activations