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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ت
    2.34
    я
    2.02
    ↡
    1.88
    كون
    1.86
    äksi
    1.77
     т
    1.70
    tenir
    1.66
    تهم
    1.65
    <unused702>
    1.64
    puede
    1.61
    POSITIVE LOGITS
     angrily
    1.80
     struggled
    1.79
     grape
    1.74
     tongs
    1.72
    own
    1.71
    m
    1.71
    heastern
    1.71
     घाटी
    1.70
    ward
    1.69
     singers
    1.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.