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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Description
    0.68
     reform
    0.68
    reform
    0.66
     també
    0.64
    }"
    0.63
    }"]
    0.62
    }\,\
    0.61
    ypen
    0.61
    }"/>
    0.61
     besk
    0.61
    POSITIVE LOGITS
     stedet
    0.75
     behest
    0.71
     здания
    0.71
     cropland
    0.70
     squats
    0.68
    ้น
    0.68
    льзя
    0.68
     unsustainable
    0.68
     поги
    0.67
     अनुया
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.