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

    Neuronpedia

    INDEX
    Explanations

    measurements, quantities, and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orient
    -0.71
     airs
    -0.67
    vertisements
    -0.64
     Dress
    -0.62
     autonom
    -0.61
    çīĪ
    -0.61
    rador
    -0.59
     democracies
    -0.59
    Ħ¢
    -0.59
     Indust
    -0.59
    POSITIVE LOGITS
     peanuts
    0.83
     impressive
    0.80
     accomplishment
    0.78
    enough
    0.76
     astronomical
    0.76
    arkable
    0.75
    amount
    0.71
     Yards
    0.71
     hefty
    0.70
     achievement
    0.70
    Act Density 0.537%

    No Known Activations