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

    Neuronpedia

    INDEX
    Explanations

    negative descriptors related to quality and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veis
    -0.15
     ÑıкÑīо
    -0.15
    _REMOTE
    -0.15
     wenn
    -0.14
     bastante
    -0.14
    iversit
    -0.14
    ÐŁÐ¾Ð´
    -0.14
    ä¸Ģä¸ĭ
    -0.14
    ológ
    -0.14
    urnal
    -0.14
    POSITIVE LOGITS
     that
    0.35
    that
    0.30
     nobody
    0.24
     ÑĩÑĤо
    0.23
    	that
    0.23
     it
    0.23
     že
    0.23
     daÃŁ
    0.21
     dass
    0.21
     rằng
    0.21
    Act Density 0.090%

    No Known Activations