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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	f
    -0.07
     decorator
    -0.07
    >this
    -0.07
    =y
    -0.07
    >k
    -0.07
    乐意
    -0.07
     gearing
    -0.07
     jeu
    -0.06
    _re
    -0.06
    	I
    -0.06
    POSITIVE LOGITS
    的距离
    0.07
    _SETTING
    0.07
     worthless
    0.07
    找个
    0.06
    бро
    0.06
    BW
    0.06
    ㎠
    0.06
     đồ
    0.06
    鲃
    0.06
    רצו
    0.06
    Act Density 0.005%

    No Known Activations