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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bara
    -0.27
    樱èĬ±
    -0.26
    lake
    -0.26
    بس
    -0.25
    ported
    -0.25
    (#)
    -0.25
    owitz
    -0.25
    ç£
    -0.24
    æĪĺéĺŁ
    -0.24
    stairs
    -0.24
    POSITIVE LOGITS
     jog
    0.29
    éĿ¢è²Į
    0.28
    æ°¸
    0.27
    lü
    0.26
    åĩłä½ķ
    0.25
    åŁ
    0.24
     disposition
    0.24
    满
    0.23
    æ¼ĵ
    0.23
    olt
    0.23
    Act Density 0.966%

    No Known Activations

    This feature has no known activations.