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

    Neuronpedia

    INDEX
    Explanations

    names related to cybersecurity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polo
    -0.66
     Shutterstock
    -0.65
    å§
    -0.64
    æĸ¹
    -0.63
     Regions
    -0.62
     Fargo
    -0.62
    ARD
    -0.62
     pony
    -0.61
     Carbuncle
    -0.61
    é¾įå¥ij士
    -0.61
    POSITIVE LOGITS
    icious
    1.28
    colm
    1.19
    ignant
    1.17
    ibu
    1.16
    adies
    1.15
    practice
    1.13
    nutrition
    1.05
    pher
    1.01
    ice
    0.98
    ady
    0.97
    Act Density 0.048%

    No Known Activations