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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gener
    -0.68
     Painter
    -0.68
     whom
    -0.66
     ãĤµ
    -0.66
     miscar
    -0.66
     pronouns
    -0.65
    ais
    -0.65
     Pruitt
    -0.59
     Buddh
    -0.58
     plur
    -0.58
    POSITIVE LOGITS
    aminer
    0.72
    acebook
    0.70
    lishes
    0.69
    pora
    0.69
    osition
    0.69
    Alert
    0.68
    ulhu
    0.66
    cation
    0.65
     Pwr
    0.64
    essage
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.