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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Should
    -0.07
     Fey
    -0.07
    paid
    -0.06
    endtime
    -0.06
     ass
    -0.06
    /pre
    -0.06
    ий
    -0.06
    TED
    -0.06
     waive
    -0.06
    temp
    -0.06
    POSITIVE LOGITS
    (buffer
    0.07
     #↵
    0.07
     &'
    0.07
    အ
    0.07
    华侨
    0.06
     Nunes
    0.06
     Luna
    0.06
    忙碌
    0.06
    供暖
    0.06
    .manual
    0.06
    Act Density 0.076%

    No Known Activations