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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     $
    1.36
    z
    1.31
     of
    1.23
    v
    1.19
    h
    1.16
    x
    1.14
    ной
    1.05
     $\
    1.05
    ě
    0.97
     S
    0.96
    POSITIVE LOGITS
    𝘰
    1.38
    𝗮
    1.34
    in
    1.32
    𝘬
    1.29
    𝘢
    1.28
    on
    1.22
    as
    1.20
    𝘮
    1.20
     あ
    1.20
    𝘪
    1.19
    Act Density 0.000%

    No Known Activations