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

    Neuronpedia

    INDEX
    Explanations

    IP addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to IP addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.85
    ãĤ£
    -0.78
     Barcl
    -0.76
    tenance
    -0.74
    ãĤ¨ãĥ«
    -0.72
    brate
    -0.71
    é¾įåĸļ士
    -0.69
    */(
    -0.68
    ctuary
    -0.68
     Dying
    -0.68
    POSITIVE LOGITS
    ython
    1.12
     IP
    0.92
     address
    0.84
     infringement
    0.79
    Os
    0.77
     addresses
    0.74
    terness
    0.73
     forwarding
    0.71
     knockout
    0.71
     spoof
    0.71
    Act Density 0.012%

    No Known Activations