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

    Neuronpedia

    INDEX
    Explanations

    references to IP addresses and related technical terms

    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
    -0.90
     Cause
    -0.81
    enegger
    -0.81
    tenance
    -0.79
     Dying
    -0.76
    child
    -0.72
    lain
    -0.71
    é¾įåĸļ士
    -0.70
     Ame
    -0.69
     Jenner
    -0.69
    POSITIVE LOGITS
    ython
    1.22
     address
    0.91
    FW
    0.87
     Address
    0.85
    Os
    0.83
    FER
    0.78
    raid
    0.78
    airs
    0.77
    PF
    0.77
    rog
    0.77
    Act Density 0.021%

    No Known Activations