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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.77
    çķ
    -0.74
    åĭ
    -0.70
     Negro
    -0.70
    endix
    -0.68
    æĪ¦
    -0.68
    advertising
    -0.68
    éļ
    -0.68
     Martian
    -0.68
    éĸ
    -0.66
    POSITIVE LOGITS
    dogs
    0.74
     hus
    0.66
    unin
    0.66
    istani
    0.64
    dump
    0.63
    upt
    0.62
     authenticity
    0.61
    lings
    0.61
    heads
    0.61
     Laur
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.