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

    Neuronpedia

    INDEX
    Explanations

    sequences of digits

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those related to statistics and data metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wart
    -0.72
    iona
    -0.68
    ique
    -0.67
    esville
    -0.66
     wart
    -0.65
    sole
    -0.65
    sonian
    -0.64
     Balk
    -0.64
    inav
    -0.63
    warts
    -0.63
    POSITIVE LOGITS
     lbs
    1.01
    lbs
    0.91
     kilograms
    0.87
     sq
    0.87
     pounds
    0.87
     crore
    0.86
     kcal
    0.84
     acres
    0.83
    ths
    0.83
     gallons
    0.79
    Act Density 0.073%

    No Known Activations