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

    Neuronpedia

    INDEX
    Explanations

    numeric values in the thousands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical sequences in large quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.70
    rival
    -0.67
     tremend
    -0.66
    ifice
    -0.66
     weakened
    -0.65
    heit
    -0.64
    warts
    -0.64
    venge
    -0.62
    ivity
    -0.61
    mercial
    -0.60
    POSITIVE LOGITS
    Hz
    1.03
    mAh
    0.96
    +
    0.95
     Hz
    0.95
     crore
    0.89
    px
    0.84
     ppm
    0.83
    gp
    0.83
    bps
    0.83
    ths
    0.81
    Act Density 0.079%

    No Known Activations