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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    deposit
    -0.09
     EW
    -0.07
     Aleppo
    -0.07
     tense
    -0.07
    .wh
    -0.07
     Psalm
    -0.07
    PAY
    -0.07
    ались
    -0.07
     Wesley
    -0.07
     male
    -0.06
    POSITIVE LOGITS
    综合利用
    0.07
    _LOG
    0.07
     Used
    0.07
    第三节
    0.07
     //////
    0.07
    ﭖ
    0.07
    _Read
    0.06
     zobaczyć
    0.06
    来到
    0.06
    ORLD
    0.06
    Act Density 0.002%

    No Known Activations