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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     simplicity
    -0.73
     misunder
    -0.71
    soDeliveryDate
    -0.68
     fract
    -0.67
    agall
    -0.67
     reconc
    -0.66
     bruising
    -0.65
     rift
    -0.65
     longitudinal
    -0.64
     bisc
    -0.64
    POSITIVE LOGITS
    793
    0.72
    641
    0.72
    238
    0.70
    552
    0.70
    886
    0.69
    427
    0.69
    }\
    0.69
     CrossRef
    0.68
    805
    0.68
    617
    0.68
    Act Density 0.075%

    No Known Activations