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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arton
    -0.84
    JM
    -0.77
     paran
    -0.70
     observers
    -0.68
     unpre
    -0.62
     Jobs
    -0.61
    keley
    -0.61
     recomm
    -0.61
    WT
    -0.61
    ¥ŀ
    -0.61
    POSITIVE LOGITS
    aser
    0.72
    eer
    0.72
    artisan
    0.71
    asonic
    0.71
    NRS
    0.69
    dra
    0.69
    phe
    0.68
    Mask
    0.68
    PLIED
    0.67
    ominium
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.