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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    сиз
    0.43
    Uncle
    0.40
    Speakers
    0.39
     Uncle
    0.38
    ＂
    0.38
     Goto
    0.37
     "
    0.36
    Palette
    0.36
    |।
    0.35
    «,
    0.35
    POSITIVE LOGITS
     ig
    0.50
     иг
    0.47
     ignore
    0.46
     ignored
    0.43
    ignore
    0.41
     Ig
    0.40
     ignores
    0.39
     igu
    0.37
    ignores
    0.37
     pass
    0.35
    Act Density 0.000%

    No Known Activations