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

    Neuronpedia

    INDEX
    Explanations

    references to corruption and corrupt practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    864
    -0.15
    rama
    -0.15
    isters
    -0.15
    ubic
    -0.14
    OutOf
    -0.14
    ëĿ¼ëıĦ
    -0.14
    adium
    -0.14
    Tube
    -0.14
    alm
    -0.14
    NU
    -0.14
    POSITIVE LOGITS
    ogne
    0.17
    تÛĮ
    0.15
    ulent
    0.15
     consolidated
    0.14
    ulence
    0.14
    ped
    0.14
    ptune
    0.13
    Ñĩай
    0.13
    ocoder
    0.13
    èݱ
    0.13
    Act Density 0.014%

    No Known Activations