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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     които
    0.80
     která
    0.73
     которого
    0.73
     (\"
    0.72
     которые
    0.71
    之类的
    0.68
    ों
    0.68
    වල
    0.68
     iaitu
    0.67
     („
    0.67
    POSITIVE LOGITS
    ’
    1.50
    '
    1.33
     doesn
    1.07
     wasn
    1.05
     happens
    1.01
     hasn
    0.98
     represents
    0.96
     involves
    0.96
     requires
    0.95
     seems
    0.92
    Act Density 0.512%

    No Known Activations