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

    Neuronpedia

    INDEX
    Explanations

    timestamps marked as "Last" in online profiles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating recent activity or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -1.03
    nai
    -0.78
    aband
    -0.75
    mbuds
    -0.70
    kaya
    -0.69
    cil
    -0.68
    uador
    -0.67
    amber
    -0.66
    apore
    -0.66
    OPLE
    -0.66
    POSITIVE LOGITS
     Gleaming
    0.87
     ditch
    0.86
     week
    0.85
     month
    0.83
     Month
    0.79
     gasp
    0.77
    fm
    0.76
     night
    0.76
     year
    0.75
     Updated
    0.73
    Act Density 0.068%

    No Known Activations