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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.55
     PagesJaunes
    -0.51
    andowski
    -0.50
    GEBURTSDATUM
    -0.48
     Monfieur
    -0.45
    MergeFrom
    -0.45
    BooleanField
    -0.45
     Infórmanos
    -0.44
     فريبيس
    -0.43
     vVar
    -0.43
    POSITIVE LOGITS
     T
    0.96
     t
    0.77
     Т
    0.67
     tâ
    0.64
     trillion
    0.64
     Trotsky
    0.62
     tə
    0.62
    T
    0.62
     트
    0.61
     ट
    0.61
    Act Density 2.350%

    No Known Activations