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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or development happening up to a certain point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating change or continuity over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tears
    -0.65
    ``
    -0.65
     Learns
    -0.64
     Benefits
    -0.61
    Choice
    -0.61
    lez
    -0.61
    umbn
    -0.60
     Extension
    -0.57
    BuyableInstoreAndOnline
    -0.56
    0010
    -0.55
    POSITIVE LOGITS
     unsus
    0.74
     unnoticed
    0.69
     belonged
    0.68
    DEN
    0.68
     hadn
    0.66
     unexplained
    0.65
     onwards
    0.65
     hasn
    0.63
     unrem
    0.62
    unknown
    0.61
    Act Density 0.053%

    No Known Activations