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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.09
    4:0.08
    5:0.07
    6:0.07
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
     Swanson
    -2.75
    sleep
    -2.58
    teenth
    -2.56
    leness
    -2.56
     Rent
    -2.53
    camp
    -2.46
     Retirement
    -2.46
     orphans
    -2.43
     Slave
    -2.38
    Sleep
    -2.37
    POSITIVE LOGITS
     laun
    3.01
    gypt
    2.89
     @@
    2.79
     confir
    2.71
    metics
    2.58
    mson
    2.56
    ��
    2.56
    =-=-=-=-
    2.48
    mington
    2.43
    モ
    2.42
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.