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

    Neuronpedia

    INDEX
    Explanations

    dates and publishing information

    oai_token-act-pair · gpt-3.5-turbo

    instances of publication dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifted
    -0.65
    ilogy
    -0.64
     Prometheus
    -0.63
    rir
    -0.62
    vernment
    -0.61
    raf
    -0.59
    porary
    -0.58
     Voldemort
    -0.58
    wagen
    -0.57
    arden
    -0.56
    POSITIVE LOGITS
     weekday
    0.86
     Feb
    0.81
     Tue
    0.74
     Wednesday
    0.71
     Aug
    0.71
     Monday
    0.71
     February
    0.71
     Apr
    0.70
     October
    0.69
     Tuesday
    0.69
    Act Density 0.030%

    No Known Activations