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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    campus
    -0.78
     researched
    -0.70
     backlog
    -0.67
    anical
    -0.67
     reviewed
    -0.64
     mishand
    -0.63
     traff
    -0.63
    uca
    -0.61
     proble
    -0.60
     risked
    -0.59
    POSITIVE LOGITS
    Kings
    0.86
    imir
    0.71
    bys
    0.70
     Sov
    0.67
     rend
    0.67
    Lay
    0.66
    vation
    0.65
     sauce
    0.64
    Pretty
    0.61
    ript
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.