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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     don
    1.23
    1.11
    don
    1.05
     didn
    1.02
     doesn
    1.02
    ON
    1.00
     iff
    0.99
     yourself
    0.98
    ght
    0.97
     টাকা
    0.95
    POSITIVE LOGITS
     பல்வேறு
    1.30
    Furthermore
    1.09
    ንዳንድ
    1.02
    The
    0.98
     गौरतलब
    0.98
    其
    0.96
     zowel
    0.95
     প্রকৃতপক্ষে
    0.95
     또한
    0.94
    ดังกล่าว
    0.93
    Act Density 0.351%

    No Known Activations