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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cont
    0.74
     Chat
    0.69
     Caught
    0.65
     Child
    0.63
     Благодаря
    0.63
     Comes
    0.62
     रखो
    0.62
    Alles
    0.62
     Goal
    0.61
     Care
    0.61
    POSITIVE LOGITS
    ق
    0.88
    ኒ
    0.88
    니
    0.87
     tão
    0.86
    म्मू
    0.79
    लिसा
    0.79
    ಗ್ಗ
    0.79
    껐
    0.78
    ্ভব
    0.77
    tLogRow
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.