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

    Neuronpedia

    INDEX
    Explanations

    numerical fractions or percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical ratios or proportions related to populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Clar
    -0.72
    idel
    -0.70
    ptr
    -0.69
    played
    -0.67
    oult
    -0.64
    flag
    -0.63
    hement
    -0.62
    jri
    -0.61
    lyak
    -0.61
    dial
    -0.60
    POSITIVE LOGITS
     (%
    0.71
     households
    0.71
     earners
    0.66
     occurrence
    0.65
    ividual
    0.64
     surveyed
    0.63
     pies
    0.63
    ighty
    0.62
     percentile
    0.61
     probability
    0.60
    Act Density 0.068%

    No Known Activations