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

    Neuronpedia

    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gpt-3.5-turbo

    percentages related to changes in financial or statistical metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issues
    -0.66
     intent
    -0.60
     rife
    -0.58
    heads
    -0.57
    pecially
    -0.56
     wisely
    -0.56
    ADD
    -0.54
    izoph
    -0.54
    inelli
    -0.53
     fodder
    -0.53
    POSITIVE LOGITS
     crore
    0.82
    ĸļ
    0.74
    isSpecialOrderable
    0.73
     GDP
    0.71
     =================================================================
    0.71
     ±
    0.70
    imeters
    0.69
    billion
    0.69
     GPA
    0.68
     squared
    0.67
    Act Density 0.173%

    No Known Activations