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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate intentions or actions, particularly starting with "To"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.52
     endregion
    -0.51
     protoimpl
    -0.48
     Bintang
    -0.47
     OMITBAD
    -0.45
     AssemblyVersion
    -0.44
    endphp
    -0.43
    /*
    -0.43
    Sú
    -0.42
     виправивши
    -0.41
    POSITIVE LOGITS
     To
    0.86
    To
    0.79
     Чтобы
    0.59
    Чтобы
    0.58
     Để
    0.57
    Для
    0.57
     Для
    0.57
    Để
    0.54
    するには
    0.53
    要想
    0.49
    Act Density 0.097%

    No Known Activations