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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵↵
    0.78
     unital
    0.63
     durations
    0.62
     states
    0.59
     chronological
    0.59
     tetap
    0.59
     chronology
    0.59
     correspondence
    0.58
     reass
    0.58
     lange
    0.58
    POSITIVE LOGITS
    But
    0.92
    <h2>
    0.91
    If
    0.91
    Important
    0.88
    <h3>
    0.86
    Although
    0.85
    In
    0.84
    For
    0.84
    Remember
    0.84
    However
    0.84
    Act Density 0.000%

    No Known Activations