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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    %%%%
    -0.71
    ktop
    -0.68
    folk
    -0.67
    ature
    -0.66
    atures
    -0.66
     Reincarn
    -0.64
    ÄŁ
    -0.63
     Bok
    -0.62
    warts
    -0.62
    ¿½
    -0.61
    POSITIVE LOGITS
     deadliest
    0.67
    natureconservancy
    0.67
    probably
    0.66
    htaking
    0.65
    uated
    0.62
    inates
    0.61
     towed
    0.61
    igated
    0.61
    uate
    0.60
     geographically
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.