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

    Neuronpedia

    INDEX
    Explanations

    years mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2009

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onite
    -0.87
    othing
    -0.70
    amins
    -0.69
    heid
    -0.67
    orable
    -0.66
    ealing
    -0.65
    esan
    -0.64
    onal
    -0.63
    kef
    -0.62
    naire
    -0.61
    POSITIVE LOGITS
    å¹
    0.84
    -'
    0.73
    06
    0.72
    08
    0.69
    master
    0.68
     onwards
    0.65
    05
    0.65
    07
    0.62
    03
    0.61
    interstitial
    0.60
    Act Density 0.019%

    No Known Activations