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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ="/
    -0.71
     Merlin
    -0.62
    eele
    -0.62
     Mehran
    -0.59
    ::::::::
    -0.58
    #$#$
    -0.57
    ãĥ¡
    -0.57
    neau
    -0.57
    ipedia
    -0.56
    rill
    -0.56
    POSITIVE LOGITS
     already
    0.87
     (=
    0.78
     (?,
    0.78
    Bay
    0.78
     (
    0.77
     [*
    0.77
     (_
    0.75
     too
    0.74
     (>
    0.72
     also
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.