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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
           ↵↵
    -0.08
    =\"#
    -0.07
    تقد
    -0.07
    "\↵
    -0.07
     Finch
    -0.07
    icol
    -0.07
    多万元
    -0.07
    管道
    -0.07
    omial
    -0.07
    quota
    -0.07
    POSITIVE LOGITS
    生生
    0.08
     SU
    0.07
    	ap
    0.07
    まれ
    0.06
    LET
    0.06
    궜
    0.06
     libert
    0.06
    ﮝ
    0.06
     Funeral
    0.06
    注意
    0.06
    Act Density 0.186%

    No Known Activations