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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tooth
    -0.72
     Agreement
    -0.67
     Riv
    -0.65
     Declaration
    -0.64
     Cruel
    -0.63
    cot
    -0.62
     Longh
    -0.61
     Prohibition
    -0.61
     Ranch
    -0.60
     Area
    -0.59
    POSITIVE LOGITS
    archive
    0.71
    utsche
    0.70
    ussia
    0.70
    astical
    0.70
    profits
    0.69
    mail
    0.69
    bus
    0.68
    astically
    0.68
    osp
    0.67
    gallery
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.