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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pol
    -0.08
     TPP
    -0.07
     paths
    -0.07
    Pr
    -0.07
    -sex
    -0.07
     terror
    -0.07
     lesion
    -0.07
    Տ
    -0.07
    שמר
    -0.07
    Io
    -0.07
    POSITIVE LOGITS
    بلاغ
    0.08
    轮廓
    0.07
    (Book
    0.07
    IGATION
    0.07
    خروج
    0.07
    _outline
    0.07
    [last
    0.07
    (distance
    0.06
    lz
    0.06
     NONE
    0.06
    Act Density 0.003%

    No Known Activations