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

    Neuronpedia

    INDEX
    Explanations

    mentions of personal experiences or events in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    events and personal milestones in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atters
    -0.68
    ivably
    -0.65
     Kremlin
    -0.62
    ãĥķãĤ¡
    -0.61
    ãĥĥãĥĪ
    -0.61
    odes
    -0.58
     wield
    -0.58
    payer
    -0.58
    pdf
    -0.58
    atories
    -0.58
    POSITIVE LOGITS
     my
    1.07
     myself
    1.00
     I
    0.91
     luckily
    0.89
    My
    0.86
     hindsight
    0.84
     reluct
    0.83
     haha
    0.82
     mornings
    0.82
    I
    0.81
    Act Density 1.114%

    No Known Activations