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

    Neuronpedia

    INDEX
    Explanations

    the phrase "out of" followed by a numerical value, indicating a proportion or percentage

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical data and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arsen
    -0.69
    Ku
    -0.67
    wake
    -0.64
     Reincarnated
    -0.64
    kefeller
    -0.63
     Miko
    -0.62
    UTERS
    -0.61
     Tao
    -0.61
     Yen
    -0.60
    avery
    -0.60
    POSITIVE LOGITS
    stretched
    0.99
    fitted
    0.94
    landers
    0.93
    lander
    0.86
    lier
    0.86
    number
    0.84
    flow
    0.82
    )=(
    0.80
    stri
    0.79
    classes
    0.77
    Act Density 0.018%

    No Known Activations