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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     DEAD
    -0.08
     defects
    -0.07
     opponent
    -0.07
     prescription
    -0.07
    ọn
    -0.07
    北斗
    -0.07
    一架
    -0.07
     mosquitoes
    -0.07
    笺
    -0.07
    事實
    -0.07
    POSITIVE LOGITS
     огр
    0.07
    lijah
    0.07
     ogląda
    0.07
    conds
    0.07
    🕝
    0.07
    _xml
    0.07
     wybrać
    0.07
    ꡓ
    0.07
    嚇
    0.07
     mówi
    0.06
    Act Density 0.025%

    No Known Activations