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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    A
    0.59
    in
    0.53
    us
    0.53
    st
    0.53
    a
    0.52
    ben
    0.50
    tn
    0.50
    nob
    0.49
    fl
    0.49
    nn
    0.49
    POSITIVE LOGITS
    芢
    0.51
     pilgr
    0.49
     את
    0.48
    ওয়া
    0.47
     忄
    0.46
     guarded
    0.46
    ческую
    0.46
     ומ
    0.46
    셰
    0.46
    闱
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.