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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    marks
    -0.82
    abouts
    -0.75
    kees
    -0.71
     Cards
    -0.68
    aneers
    -0.66
     Machines
    -0.66
     Hots
    -0.65
    boot
    -0.65
     Downloads
    -0.63
    mination
    -0.62
    POSITIVE LOGITS
    utherford
    0.71
    ueller
    0.70
    eele
    0.67
    icit
    0.67
     fentanyl
    0.65
     fug
    0.64
     severed
    0.64
    riction
    0.63
    NRS
    0.62
     unicorn
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.