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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and discussions surrounding societal issues and human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Disclosure
    -0.15
     Bez
    -0.15
    mdi
    -0.14
    iben
    -0.14
    رÙĪز
    -0.14
    argon
    -0.14
    812
    -0.14
    adu
    -0.14
    -Ta
    -0.14
    814
    -0.14
    POSITIVE LOGITS
    inae
    0.15
    clearfix
    0.15
    %C
    0.14
    dana
    0.14
    ãĤ¹ãĥ¬
    0.14
    ìĥģìĿĺ
    0.14
    owler
    0.13
    ucht
    0.13
     beste
    0.13
     groove
    0.13
    Act Density 0.001%

    No Known Activations