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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    at
    0.78
     d
    0.75
    ig
    0.75
    in
    0.72
    aw
    0.70
    akit
    0.70
    w
    0.69
    9
    0.69
    ↵↵
    0.68
    co
    0.68
    POSITIVE LOGITS
     halfCanvas
    0.92
     polytopes
    0.91
     Eurostile
    0.89
     одной
    0.89
     старије
    0.89
     लड्ड
    0.89
     almighty
    0.87
    cccnc
    0.87
     orale
    0.86
     touchdowns
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.