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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .Scheme
    -0.08
     Fantasy
    -0.08
    Dialog
    -0.08
    Deadline
    -0.07
     Northwestern
    -0.07
    (__('
    -0.07
    _period
    -0.07
    网投
    -0.07
    (Error
    -0.07
    /title
    -0.06
    POSITIVE LOGITS
     using
    0.07
     להביא
    0.07
    something
    0.07
    essential
    0.07
    ascending
    0.06
     pe
    0.06
    η
    0.06
     التعليم
    0.06
    коль
    0.06
    министр
    0.06
    Act Density 0.061%

    No Known Activations