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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical percentages and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.81
     Tayyip
    -0.77
    ieties
    -0.73
    sbm
    -0.72
     Horizons
    -0.71
     Tycoon
    -0.70
    Merit
    -0.70
    itans
    -0.69
    IRT
    -0.67
    ÄŁ
    -0.67
    POSITIVE LOGITS
    pointer
    0.86
     percentage
    0.77
     (%)
    0.75
    antry
    0.75
    hetically
    0.73
     percentages
    0.72
    ttle
    0.72
    pointers
    0.72
     accuracy
    0.71
    assed
    0.71
    Act Density 0.023%

    No Known Activations