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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    coded
    -0.15
    ÑĤÑĢо
    -0.15
    ">//
    -0.15
    adow
    -0.14
    ASTER
    -0.14
    curl
    -0.14
    ENE
    -0.14
    Criteria
    -0.14
    adaÅŁ
    -0.14
    cour
    -0.14
    POSITIVE LOGITS
     C
    0.31
    (C
    0.30
    .c
    0.29
     c
    0.28
    _c
    0.27
    .C
    0.27
    ÂłC
    0.27
    (c
    0.26
    _C
    0.25
    $c
    0.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.