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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reuse
    -0.79
     distribute
    -0.66
     subscriber
    -0.66
     neighbors
    -0.64
     organized
    -0.64
     unrestricted
    -0.62
     Scope
    -0.62
     triv
    -0.61
     subscribers
    -0.61
     ranc
    -0.61
    POSITIVE LOGITS
    err
    0.86
    bourg
    0.85
    ãģĨ
    0.76
    unic
    0.74
    ris
    0.74
    olver
    0.74
    usc
    0.73
    IFF
    0.73
    roman
    0.72
    ray
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.