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

    Neuronpedia

    INDEX
    Explanations

    large numbers of people or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values representing millions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.73
    alid
    -0.71
    Discuss
    -0.70
     Dating
    -0.70
    ourage
    -0.68
    rade
    -0.66
     distingu
    -0.66
    cade
    -0.66
    ulhu
    -0.65
    sonian
    -0.65
    POSITIVE LOGITS
     dollars
    1.10
     hectares
    1.05
    aires
    0.97
     pounds
    0.96
     lbs
    0.95
     tonnes
    0.92
     yuan
    0.91
     acres
    0.89
     sq
    0.88
    lb
    0.88
    Act Density 0.062%

    No Known Activations