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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values, particularly those related to large quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.87
     Prelude
    -0.76
    sole
    -0.72
    mercial
    -0.70
    venge
    -0.68
    sid
    -0.65
    rival
    -0.63
    abus
    -0.62
    chart
    -0.61
    aura
    -0.60
    POSITIVE LOGITS
    bps
    0.90
    MHz
    0.89
     crore
    0.84
     acres
    0.82
    mph
    0.82
     miles
    0.82
     hectares
    0.81
    +
    0.78
    mAh
    0.78
     lbs
    0.78
    Act Density 0.071%

    No Known Activations