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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Oo
    -0.76
    istar
    -0.76
     DK
    -0.66
     Virus
    -0.63
     AGA
    -0.62
     rewarded
    -0.61
     Bethesda
    -0.60
     Incarn
    -0.60
     Brave
    -0.59
     HS
    -0.59
    POSITIVE LOGITS
    icago
    0.81
    essor
    0.76
    cius
    0.75
    alus
    0.75
     lapse
    0.75
    uth
    0.69
     swirl
    0.69
    intendent
    0.69
    ucl
    0.69
    umn
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.