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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    netflix
    -0.67
     rampage
    -0.66
    erate
    -0.65
     Medicare
    -0.63
     survivor
    -0.62
     initiation
    -0.62
    nown
    -0.61
    includes
    -0.60
     continuation
    -0.59
     amnesty
    -0.59
    POSITIVE LOGITS
    alys
    0.76
    alogue
    0.72
    aniel
    0.70
    Cu
    0.68
    ãĥ¢
    0.67
    zers
    0.67
     Drawn
    0.67
     Sparrow
    0.66
    baugh
    0.65
    ected
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.