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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or qualifications in contexts involving formal decisions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umont
    -0.17
    à¹ĩà¸Ļà¸ķ
    -0.14
     Som
    -0.14
    ваниÑı
    -0.14
    害
    -0.13
    å¥ı
    -0.13
     Bugs
    -0.13
    ushman
    -0.13
     Meer
    -0.13
    ÑģÑıÑĤ
    -0.13
    POSITIVE LOGITS
     aconte
    0.17
     happened
    0.17
     happen
    0.16
     happens
    0.16
     happening
    0.15
    ekk
    0.15
     Jens
    0.15
    mos
    0.15
    aeda
    0.14
    rint
    0.14
    Act Density 0.338%

    No Known Activations