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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantity or size

    oai_token-act-pair · gpt-3.5-turbo

    repeated numerical values related to quantities, often in the thousands or high ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouri
    -0.80
    uality
    -0.79
    itcher
    -0.79
    imentary
    -0.78
    rosso
    -0.77
    cho
    -0.75
    stood
    -0.73
    alde
    -0.72
    ration
    -0.72
    ese
    -0.71
    POSITIVE LOGITS
    mAh
    1.10
    8000
    0.83
     ILCS
    0.78
     certs
    0.78
     rpm
    0.73
     NOTICE
    0.73
     Yen
    0.71
     MHz
    0.69
     msec
    0.68
    cffff
    0.68
    Act Density 0.011%

    No Known Activations