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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Dragonbound
    -0.81
    Browser
    -0.74
    enting
    -0.74
    ynes
    -0.73
    amate
    -0.71
    ICLE
    -0.69
    heter
    -0.68
    ocaust
    -0.67
    Psy
    -0.66
    fired
    -0.64
    POSITIVE LOGITS
    ¥µ
    0.67
    wikipedia
    0.66
     partly
    0.65
     altogether
    0.62
     buck
    0.60
    iron
    0.60
    Ö¼
    0.59
     Gand
    0.59
     Barg
    0.58
     Knot
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.