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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ste
    -0.08
    osen
    -0.07
    낸
    -0.07
     marginLeft
    -0.07
    affer
    -0.06
    	cerr
    -0.06
    认真
    -0.06
    ahl
    -0.06
     따른
    -0.06
    ㅆ
    -0.06
    POSITIVE LOGITS
     selfie
    0.08
     boarding
    0.07
     trackers
    0.07
    人性
    0.07
     binaries
    0.07
    شروط
    0.07
    _FREQUENCY
    0.07
    .iOS
    0.07
     duplex
    0.07
     incidence
    0.07
    Act Density 0.000%

    No Known Activations