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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ún
    0.64
     smashed
    0.63
     crumbled
    0.61
    賄
    0.60
    Uns
    0.60
     clover
    0.60
    一片
    0.59
     neglected
    0.58
    檻
    0.58
     trailbl
    0.57
    POSITIVE LOGITS
     tijekom
    0.76
     during
    0.68
    梩
    0.67
    ,--
    0.63
     ().
    0.62
    ,-\
    0.62
    during
    0.62
    (),
    0.61
     perpend
    0.60
    ();
    0.60
    Act Density 2.073%

    No Known Activations