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

    Neuronpedia

    INDEX
    Explanations

    numbers with high values that may be related to statistics or records

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bened
    -0.70
    sole
    -0.70
    sonian
    -0.69
    pson
    -0.66
    iona
    -0.65
    esville
    -0.62
    infeld
    -0.61
    ique
    -0.61
     Balk
    -0.61
     Mub
    -0.61
    POSITIVE LOGITS
     lbs
    0.93
    ths
    0.93
     kilograms
    0.90
     pounds
    0.89
     crore
    0.85
    lbs
    0.84
     gallons
    0.83
     miles
    0.80
     acres
    0.80
     kilometers
    0.79
    Act Density 0.077%

    No Known Activations