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

    Neuronpedia

    INDEX
    Explanations

    conditional and definitional phrases used in mathematical statements or proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fign
    -0.59
    readAs
    -0.56
    habhar
    -0.55
    ustice
    -0.55
    Bretagne
    -0.55
    うん
    -0.53
    icorn
    -0.52
     Wissenschaft
    -0.51
     thefe
    -0.51
    ждый
    -0.51
    POSITIVE LOGITS
    ọi
    1.08
     Let
    0.82
    Пусть
    0.78
    Suppose
    0.78
    Let
    0.77
    ặt
    0.76
    djangoproject
    0.71
     Suppose
    0.69
    GEBURTSDATUM
    0.68
    BeginContext
    0.68
    Act Density 0.752%

    No Known Activations