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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _s
    -0.07
    Helper
    -0.07
    钡
    -0.07
    찮
    -0.07
     dip
    -0.07
     sobie
    -0.07
     desea
    -0.07
    מדי
    -0.07
     어떻
    -0.07
    הלך
    -0.06
    POSITIVE LOGITS
    ata
    0.07
     figured
    0.07
     ................
    0.07
    设置了
    0.07
    -ch
    0.07
    Mount
    0.06
    ="@
    0.06
    пла
    0.06
    вших
    0.06
    favorite
    0.06
    Act Density 0.029%

    No Known Activations