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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of the term 'Inf' or 'Infractions'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company "Infosis."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.93
    manship
    -0.89
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.87
    BOOK
    -0.87
    âķIJâķIJ
    -0.79
    pload
    -0.77
    OPLE
    -0.76
    DragonMagazine
    -0.76
    姫
    -0.75
    æĢ
    -0.75
    POSITIVE LOGITS
    iltr
    1.11
    lamm
    1.03
    rared
    1.02
    ertility
    0.99
    ocom
    0.98
    acet
    0.97
    icult
    0.95
    ractions
    0.94
    iltration
    0.94
    onso
    0.90
    Act Density 0.006%

    No Known Activations