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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and the impact of leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æļ
    -0.15
    iese
    -0.14
     INCLUDING
    -0.13
     ayrıca
    -0.13
    æĺ¯ä»Ģä¹Ī
    -0.13
    åĮħæĭ¬
    -0.13
    iyon
    -0.13
     gá»ĵm
    -0.13
    aled
    -0.13
    orthand
    -0.13
    POSITIVE LOGITS
     напÑĢимеÑĢ
    0.33
     etc
    0.33
     ÙħØ«ÙĦا
    0.29
     example
    0.29
     exemplo
    0.24
     напÑĢиклад
    0.23
    etc
    0.23
     exemple
    0.23
    example
    0.22
    ãģªãģ©
    0.22
    Act Density 0.576%

    No Known Activations