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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    formed
    -0.27
    æĥħæĻ¯
    -0.26
    åħ·ä½ĵæĥħåĨµ
    -0.26
     wait
    -0.25
    åĨµ
    -0.24
    zburg
    -0.24
     composed
    -0.24
     Wait
    -0.24
     caused
    -0.24
    ä¸Ģä½ĵåĮĸ
    -0.23
    POSITIVE LOGITS
    çĥŃæĴŃ
    0.31
    è¿ĩåİ»
    0.28
    鼶ç¢İ
    0.28
    鼶
    0.27
    姥
    0.27
     #__
    0.27
    è¿ĩåİ»çļĦ
    0.26
    身
    0.26
    èĢĥçĤ¹
    0.26
    éģİåİ»
    0.25
    Act Density 0.004%

    No Known Activations

    This feature has no known activations.