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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     alien
    -0.08
    닌
    -0.08
    eker
    -0.08
    -den
    -0.08
     женщин
    -0.07
    ﱴ
    -0.07
    /sign
    -0.07
     POSITION
    -0.07
     resident
    -0.07
    獨立
    -0.07
    POSITIVE LOGITS
     libraries
    0.08
    ẫ
    0.07
    手册
    0.07
     amis
    0.07
     profes
    0.06
    醒目
    0.06
    Patch
    0.06
    וצר
    0.06
     Results
    0.06
    ynamodb
    0.06
    Act Density 0.099%

    No Known Activations