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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sexual
    -0.07
     foundations
    -0.07
     Norm
    -0.07
    ENO
    -0.07
    那就是
    -0.07
    信念
    -0.07
    czy
    -0.07
     nächsten
    -0.07
     בעיקר
    -0.07
     그리고
    -0.07
    POSITIVE LOGITS
     Saturdays
    0.08
    התחלה
    0.07
     teacher
    0.07
    时间
    0.07
    もら
    0.07
    /tinyos
    0.07
    荮
    0.07
    首创
    0.06
    /fwlink
    0.06
    "),"
    0.06
    Act Density 0.011%

    No Known Activations