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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.72
    ded
    -0.71
    acter
    -0.67
    Rum
    -0.66
    é¾įåĸļ士
    -0.66
    cal
    -0.66
     maj
    -0.61
     Warp
    -0.61
     arr
    -0.60
    deep
    -0.60
    POSITIVE LOGITS
     Flavoring
    0.86
    ictionary
    0.83
    zai
    0.77
    umblr
    0.76
    restling
    0.75
    enhagen
    0.71
    chin
    0.69
    tsky
    0.66
    emporary
    0.65
    gaard
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.