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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    公办
    -0.07
     tho
    -0.07
     trông
    -0.07
    砣
    -0.07
    andles
    -0.06
     nuôi
    -0.06
    concert
    -0.06
     Diễn
    -0.06
     이게
    -0.06
     Diy
    -0.06
    POSITIVE LOGITS
     extern
    0.07
     @"
    0.07
    될
    0.07
    stitution
    0.07
     Jake
    0.06
    _registry
    0.06
     Making
    0.06
    רוק
    0.06
    就會
    0.06
     subtract
    0.06
    Act Density 0.071%

    No Known Activations