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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     중국
    -0.07
     tram
    -0.07
    ids
    -0.07
     ingr
    -0.06
    談
    -0.06
    /all
    -0.06
     ceil
    -0.06
     بد
    -0.06
    阻止
    -0.06
    中原
    -0.06
    POSITIVE LOGITS
    做得
    0.07
    (place
    0.07
     действие
    0.07
    .rm
    0.07
     דול
    0.07
    exchange
    0.06
     unmatched
    0.06
    ointment
    0.06
     водо
    0.06
    很强
    0.06
    Act Density 0.008%

    No Known Activations