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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     obsługi
    -0.07
    充
    -0.07
    �
    -0.07
    ใส
    -0.07
     suffers
    -0.07
     sift
    -0.06
     carrier
    -0.06
    ользов
    -0.06
     person
    -0.06
    boy
    -0.06
    POSITIVE LOGITS
     newPath
    0.08
    鞭
    0.07
    Opening
    0.07
     archives
    0.07
     Başbakan
    0.07
     Countdown
    0.07
    阎
    0.07
    募资
    0.07
     counterpart
    0.07
    [`
    0.07
    Act Density 0.006%

    No Known Activations