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

    Neuronpedia

    INDEX
    Explanations

    references to IP addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gridy
    -0.67
    RegistryLite
    -0.66
     iprot
    -0.65
     identité
    -0.62
     surla
    -0.62
    lossians
    -0.61
     ]}
    -0.61
    sore
    -0.61
     Vikipedi
    -0.61
     duquel
    -0.60
    POSITIVE LOGITS
    ip
    0.98
     backward
    0.84
    backward
    0.71
    IP
    0.70
     Backward
    0.69
     backwards
    0.61
     aggressive
    0.59
    ipe
    0.58
    ERROR
    0.57
    Aggressive
    0.57
    Act Density 0.093%

    No Known Activations