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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Gale
    -0.08
    dzi
    -0.07
    秉
    -0.07
     Oz
    -0.07
    Drug
    -0.07
     resemble
    -0.06
    万里
    -0.06
    ari
    -0.06
     Alaska
    -0.06
     bk
    -0.06
    POSITIVE LOGITS
     deprecated
    0.08
     equalTo
    0.07
    숍
    0.07
    ウォ
    0.07
     servicing
    0.07
    ﱋ
    0.07
     Ấn
    0.07
    ערות
    0.07
    本田
    0.07
    stein
    0.07
    Act Density 0.003%

    No Known Activations