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

    Neuronpedia

    INDEX
    Explanations

    references to "people" and their connected rights or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìľ¨
    -0.17
    uber
    -0.17
    inia
    -0.16
    olia
    -0.14
    asca
    -0.14
    aber
    -0.14
     reck
    -0.14
    ault
    -0.14
    fers
    -0.14
     Ding
    -0.14
    POSITIVE LOGITS
    zik
    0.16
    827
    0.15
    اÙĨÚ¯
    0.15
    üstü
    0.15
     adult
    0.15
    ãģ¡ãģ¯
    0.14
    /org
    0.14
    brace
    0.13
     Ric
    0.13
     disarm
    0.13
    Act Density 0.046%

    No Known Activations