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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     indie
    -0.09
    เสม
    -0.08
    וול
    -0.07
    entai
    -0.07
    rę
    -0.07
    oltip
    -0.07
    ieten
    -0.07
    Viewport
    -0.07
    掳
    -0.06
     vidé
    -0.06
    POSITIVE LOGITS
    "}
    0.08
    下降
    0.08
     Mike
    0.08
    ﹣
    0.07
     strong
    0.07
    激
    0.07
     completion
    0.07
     posterior
    0.07
    -long
    0.07
    文学
    0.07
    Act Density 0.030%

    No Known Activations