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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tou
    -0.69
     Dynasty
    -0.62
     buckle
    -0.61
     headed
    -0.61
     Hats
    -0.59
     Wolves
    -0.59
     Bulls
    -0.58
     Tears
    -0.58
     dyed
    -0.58
     heading
    -0.57
    POSITIVE LOGITS
    INO
    0.74
    aucus
    0.71
    uno
    0.69
    arcer
    0.68
    HCR
    0.68
    ERN
    0.66
    flix
    0.66
    itudinal
    0.66
    ARB
    0.65
     Swap
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.