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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xit
    -0.66
     Revel
    -0.66
     Bosh
    -0.63
     Cheong
    -0.61
    urized
    -0.61
    olphins
    -0.59
     Compton
    -0.58
     Wiz
    -0.57
     subsequ
    -0.57
     Brus
    -0.56
    POSITIVE LOGITS
    lé
    0.76
    âĹı
    0.67
    leading
    0.64
    union
    0.62
    written
    0.62
    posing
    0.61
    stant
    0.60
    usk
    0.60
    writing
    0.59
     anonymously
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.