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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     real
    0.50
     cz
    0.44
     PS
    0.43
     ruf
    0.43
     Terrible
    0.43
     Dont
    0.42
     Cant
    0.41
     Seems
    0.40
     Ps
    0.40
     реа
    0.39
    POSITIVE LOGITS
    "
    0.56
    _"
    0.52
    "...
    0.51
    "，
    0.49
    "(
    0.47
    "。
    0.47
    "%
    0.46
    "<
    0.46
     #"
    0.45
     "
    0.45
    Act Density 0.000%

    No Known Activations