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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     graveyard
    -0.07
     Başbakan
    -0.07
    אזור
    -0.07
     philosophical
    -0.07
     adapt
    -0.07
    -Disposition
    -0.06
     collaborated
    -0.06
     Padres
    -0.06
     AuthenticationService
    -0.06
     deterioration
    -0.06
    POSITIVE LOGITS
    /tr
    0.07
    xA
    0.07
    قضا
    0.07
    �
    0.07
    要用
    0.07
    сто
    0.07
    ouch
    0.07
     FPS
    0.06
    游戏操作
    0.06
    的手
    0.06
    Act Density 0.045%

    No Known Activations