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

    Neuronpedia

    INDEX
    Explanations

    numerical types, specifically doubles and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.70
    (!__
    -0.69
    irre
    -0.67
     McCar
    -0.66
    __(/*!
    -0.65
    gantian
    -0.63
    +'</
    -0.62
    GHIJKLM
    -0.61
     Selection
    -0.59
    AutoScale
    -0.58
    POSITIVE LOGITS
    double
    0.90
     Kuba
    0.73
    VIAF
    0.73
    makeText
    0.72
    float
    0.70
     TPE
    0.70
    BigDecimal
    0.68
    nextDouble
    0.66
    uanto
    0.65
     Alegre
    0.65
    Act Density 0.072%

    No Known Activations