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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nesota
    -0.75
     narrowed
    -0.70
    blance
    -0.69
    ickets
    -0.69
    itech
    -0.68
     brakes
    -0.67
    haus
    -0.67
    acher
    -0.67
     ILCS
    -0.66
     cannabin
    -0.64
    POSITIVE LOGITS
    ariat
    0.73
    eat
    0.69
     Cyrus
    0.65
    yd
    0.62
    ocracy
    0.62
    adan
    0.61
    ij士
    0.61
     Daryl
    0.61
    Eat
    0.61
    adder
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.