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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.53
    log
    1.50
    tan
    1.32
    ll
    1.29
    t
    1.19
    tnie
    1.18
    tní
    1.17
    target
    1.15
    ς
    1.14
    try
    1.13
    POSITIVE LOGITS
     Belvedere
    1.28
    粕
    1.28
    ри
    1.27
    খানে
    1.24
    䊂
    1.23
    ্পনিক
    1.23
     Cavalry
    1.21
     synthase
    1.21
     complications
    1.19
    ので
    1.18
    Act Density 0.000%

    No Known Activations