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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tag
    0.52
    apparent
    0.51
    arith
    0.50
    tom
    0.49
    tar
    0.48
    compar
    0.47
    2
    0.47
    4
    0.47
    roth
    0.46
     dieting
    0.46
    POSITIVE LOGITS
    ன்
    0.48
     Jawaharlal
    0.45
     véh
    0.44
     dayan
    0.44
     Emperors
    0.44
     Emperor
    0.43
    ＮＡＮＡ
    0.43
     సామ
    0.42
    涳
    0.42
    ველი
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.