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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Wolver
    -0.69
    Bone
    -0.68
     Pav
    -0.67
    selves
    -0.66
     Cosponsors
    -0.65
     Yao
    -0.64
    worldly
    -0.64
     DRAG
    -0.62
     Hend
    -0.61
     Buc
    -0.61
    POSITIVE LOGITS
    jriwal
    0.87
    enhagen
    0.79
     horizont
    0.76
     democrat
    0.73
    orno
    0.67
    udeau
    0.66
    elsen
    0.66
     ILCS
    0.66
    utical
    0.66
     democracies
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.