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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ，$
    0.77
     fucking
    0.72
    ientôt
    0.72
    ेक्षित
    0.71
    FProperties
    0.71
    ͒
    0.70
    म्मू
    0.69
    ！）
    0.69
    ၡ
    0.69
     sogen
    0.67
    POSITIVE LOGITS
     (
    5.75
    （
    4.19
     （
    3.91
    (
    3.36
     ((
    2.89
     (\
    2.78
     (_
    2.77
     (!
    2.72
    ”（
    2.63
     (=
    2.61
    Act Density 4.279%

    No Known Activations