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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    actionDate
    -0.66
    ktop
    -0.62
     arous
    -0.61
     revealing
    -0.61
    rage
    -0.60
     Shards
    -0.59
    flower
    -0.58
     affecting
    -0.58
     Tickets
    -0.58
     facing
    -0.56
    POSITIVE LOGITS
     horm
    0.81
    ties
    0.71
    ahime
    0.70
    é¾įå
    0.69
    ãĥ¼ãĥĨãĤ£
    0.69
    inka
    0.67
    ãĥ³ãĤ¸
    0.66
     sacrific
    0.65
     contrace
    0.65
    iott
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.