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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     reg
    -0.07
     Indie
    -0.07
    upa
    -0.07
     Euro
    -0.07
    izzare
    -0.07
    )?$
    -0.07
     Mine
    -0.07
     President
    -0.07
    蛋
    -0.07
     import
    -0.07
    POSITIVE LOGITS
     glanced
    0.07
     особенно
    0.07
    猛然
    0.07
    ﹼ
    0.07
     consistently
    0.07
     нарушен
    0.07
    (example
    0.07
    避け
    0.07
    ಊ
    0.07
    窥
    0.07
    Act Density 0.002%

    No Known Activations