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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    escription
    -1.00
    enegger
    -0.92
    ufact
    -0.92
    ortium
    -0.87
    acebook
    -0.86
    ebin
    -0.85
    arij
    -0.84
    avorite
    -0.84
     referen
    -0.82
    retty
    -0.82
    POSITIVE LOGITS
     after
    0.86
     as
    0.86
     in
    0.81
     at
    0.81
     to
    0.74
     the
    0.73
     even
    0.72
     it
    0.70
     that
    0.69
     on
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.