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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    åĮł
    -0.30
    isan
    -0.28
    æĺ¯åIJ¦æľī
    -0.27
    ç«Ļéķ¿
    -0.26
    æĬĢæľ¯äººåijĺ
    -0.26
    acker
    -0.26
    asses
    -0.25
    jured
    -0.25
    .executor
    -0.25
    èªĵ
    -0.25
    POSITIVE LOGITS
    读åIJİ
    0.27
    .getOutputStream
    0.26
     rare
    0.26
    IJľ
    0.23
     Portions
    0.23
    æµ·æ¹¾
    0.23
     kitty
    0.23
    ENCE
    0.23
    ÃŃd
    0.23
    EEE
    0.23
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.