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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional or procedural statements related to decision-making and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ineno
    -0.59
    slidesToShow
    -0.56
    HomeAsUp
    -0.55
    الثة
    -0.53
    Bold
    -0.51
     wahr
    -0.51
    SaveChanges
    -0.50
    Biographie
    -0.50
    RegressionTest
    -0.49
    upassen
    -0.48
    POSITIVE LOGITS
     already
    0.76
    already
    0.67
     Already
    0.66
     ALREADY
    0.62
    ALREADY
    0.60
    Already
    0.60
    已
    0.59
    0.58
    Existing
    0.57
     existing
    0.56
    Act Density 0.600%

    No Known Activations