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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     brushes
    -0.78
    taboola
    -0.72
     weeds
    -0.67
     weed
    -0.66
     pages
    -0.65
    Mos
    -0.65
     Flavoring
    -0.64
     Cambod
    -0.64
    rise
    -0.64
    frames
    -0.63
    POSITIVE LOGITS
    ===
    0.80
    oaded
    0.77
    angelo
    0.77
     TA
    0.66
    itial
    0.66
    forcement
    0.65
    BALL
    0.65
    upload
    0.64
    TT
    0.63
     PLUS
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.