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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    avorite
    -0.75
    alog
    -0.72
     globalization
    -0.71
     Titanic
    -0.71
    ombat
    -0.68
    ailability
    -0.66
     practition
    -0.66
    achev
    -0.66
     undermin
    -0.64
    eatures
    -0.64
    POSITIVE LOGITS
    venge
    0.77
    optional
    0.74
    figure
    0.70
    fig
    0.68
    ext
    0.66
    rou
    0.66
    door
    0.66
    etry
    0.65
    part
    0.65
    owe
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.