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

    Neuronpedia

    INDEX
    Explanations

    numbers and data related to scores, targets, projections, and calculations

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to scores or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.92
    rir
    -0.86
    VPN
    -0.80
    ecast
    -0.77
     Swordsman
    -0.76
    fur
    -0.74
    ̶
    -0.73
    idable
    -0.73
    opol
    -0.70
    oso
    -0.69
    POSITIVE LOGITS
     estimates
    1.43
     estimate
    1.40
     totals
    1.39
     averages
    1.39
     numbers
    1.35
     values
    1.32
     results
    1.31
     rates
    1.29
     percentages
    1.29
     measurements
    1.28
    Act Density 0.574%

    No Known Activations