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

    Neuronpedia

    INDEX
    Explanations

    specific measurements and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations of measurements and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.72
    iqueness
    -0.71
    eele
    -0.67
    blance
    -0.67
    umenthal
    -0.66
    llah
    -0.65
    oleon
    -0.64
    uously
    -0.64
    ESA
    -0.63
    ailability
    -0.63
    POSITIVE LOGITS
    USD
    0.79
    adelphia
    0.70
     cones
    0.70
    thur
    0.70
     Mehran
    0.67
    ï¸ı
    0.66
    390
    0.66
     ponds
    0.66
    eper
    0.65
    teenth
    0.64
    Act Density 0.195%

    No Known Activations