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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    APD
    -0.74
    ãĤ´
    -0.69
     Ubisoft
    -0.61
     Pwr
    -0.61
     interns
    -0.60
    RESULTS
    -0.60
     writers
    -0.59
     OU
    -0.58
     Barron
    -0.57
     Dove
    -0.57
    POSITIVE LOGITS
    shut
    0.70
    anus
    0.69
    course
    0.69
    oeuv
    0.68
    idget
    0.65
    cffff
    0.65
    rouch
    0.63
    thinkable
    0.62
    dain
    0.61
     ][
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.