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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aign
    -0.82
    ĸļ
    -0.78
    taboola
    -0.77
    merce
    -0.77
    uster
    -0.73
    @#&
    -0.69
     sway
    -0.69
     chant
    -0.68
    ometimes
    -0.67
    rup
    -0.63
    POSITIVE LOGITS
     Ghosts
    0.70
    yi
    0.69
    olas
    0.69
    culosis
    0.68
     Aval
    0.65
    inas
    0.64
    âĦ¢:
    0.63
     twins
    0.62
    omy
    0.62
     Wheels
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.