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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    an
    1.31
    n
    1.28
     as
    1.17
    re
    1.12
    c
    1.12
    as
    1.10
    st
    1.10
    $
    1.06
    in
    1.05
    ن
    1.05
    POSITIVE LOGITS
    ás
    1.22
     với
    1.13
    性が
    1.07
    т
    1.05
     ότι
    1.02
    ъ
    1.02
    й
    1.00
     що
    0.98
    ică
    0.97
     I
    0.96
    Act Density 0.000%

    No Known Activations