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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    f
    1.37
    <0x80>
    1.16
    ok
    1.14
    0
    1.14
    res
    1.04
    дри
    1.00
    an
    0.95
    ad
    0.95
    ０
    0.95
    unn
    0.92
    POSITIVE LOGITS
    ↵↵
    1.41
     on
    1.34
    म
    1.33
    ید
    1.22
    UM
    1.21
     that
    1.19
     trow
    1.16
    ll
    1.14
    ли
    1.13
     que
    1.12
    Act Density 0.000%

    No Known Activations