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

    Neuronpedia

    INDEX
    Explanations

    numbers and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osite
    -0.76
    Keys
    -0.75
    kt
    -0.73
    iol
    -0.71
    iatrics
    -0.70
    OY
    -0.69
    Frame
    -0.67
    Different
    -0.67
    onomy
    -0.67
    aca
    -0.67
    POSITIVE LOGITS
     what
    0.87
     comparable
    0.77
     the
    0.74
    lihood
    0.74
     enough
    0.71
     average
    0.70
     equivalent
    0.69
     any
    0.69
     neighboring
    0.67
     those
    0.67
    Act Density 0.134%

    No Known Activations