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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .bb
    -0.07
    過來
    -0.07
     hè
    -0.07
    (Page
    -0.07
    פח
    -0.07
    _BUFF
    -0.07
    iversary
    -0.06
    在床上
    -0.06
    涼
    -0.06
     board
    -0.06
    POSITIVE LOGITS
    毡
    0.08
    _t
    0.07
    stud
    0.07
     contact
    0.07
     Sl
    0.07
    气氛
    0.07
    犊
    0.06
    -Am
    0.06
     daring
    0.06
    advert
    0.06
    Act Density 0.070%

    No Known Activations