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

    Neuronpedia

    INDEX
    Explanations

    percentage or number values associated with changes or comparisons

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hid
    -0.74
    rology
    -0.70
    sit
    -0.69
    enes
    -0.67
    ritis
    -0.67
    wine
    -0.66
    LA
    -0.65
    rar
    -0.65
    rera
    -0.64
     largeDownload
    -0.64
    POSITIVE LOGITS
     leaps
    1.04
     virtue
    0.86
     fiat
    0.86
     2030
    0.84
     20
    0.81
     50
    0.80
     fractions
    0.79
     trillions
    0.79
     approximately
    0.76
     2050
    0.76
    Act Density 0.041%

    No Known Activations