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

    Neuronpedia

    INDEX
    Explanations

    large numbers mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical quantities related to people or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiz
    -0.83
    ufact
    -0.77
    venge
    -0.76
    sole
    -0.73
    nam
    -0.71
    abus
    -0.70
    rival
    -0.70
    comes
    -0.70
    alys
    -0.69
     tremend
    -0.69
    POSITIVE LOGITS
     hectares
    0.96
    +
    0.96
    gp
    0.94
     lbs
    0.94
     acres
    0.93
     pounds
    0.92
     miles
    0.89
    IU
    0.89
    lb
    0.87
     gallons
    0.87
    Act Density 0.065%

    No Known Activations