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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	target
    -0.07
     roz
    -0.07
    抢
    -0.07
    .non
    -0.07
    $title
    -0.06
    难民
    -0.06
    лож
    -0.06
    (CONFIG
    -0.06
    놈
    -0.06
     kullanıcı
    -0.06
    POSITIVE LOGITS
    eiß
    0.07
    🚵
    0.07
     CU
    0.06
    rowning
    0.06
     fetus
    0.06
    Inserted
    0.06
     upsetting
    0.06
    Sq
    0.06
     Amend
    0.06
     por
    0.06
    Act Density 0.061%

    No Known Activations