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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     coût
    -0.28
     Hannity
    -0.27
     Caucus
    -0.27
     homosex
    -0.26
    彩ç¥ŀ
    -0.26
    remely
    -0.26
     hete
    -0.26
    autiful
    -0.26
     MainMenu
    -0.25
    ßĹ
    -0.25
    POSITIVE LOGITS
    æ¯ģ
    0.29
    纪
    0.28
    own
    0.28
    onom
    0.27
     ÐĶмиÑĤÑĢ
    0.26
    BM
    0.26
    sm
    0.26
    SSERT
    0.26
    OU
    0.26
    IEL
    0.25
    Act Density 0.898%

    No Known Activations

    This feature has no known activations.