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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    PDF
    -0.70
    HUD
    -0.70
     Polk
    -0.68
    BIL
    -0.67
     Pegasus
    -0.66
    CM
    -0.63
    KY
    -0.62
    Code
    -0.62
    Pocket
    -0.62
     Skydragon
    -0.62
    POSITIVE LOGITS
     allerg
    0.83
    netflix
    0.81
     allergies
    0.76
     sauces
    0.74
     "$:/
    0.68
    pmwiki
    0.66
     smell
    0.64
    allo
    0.63
     retard
    0.62
    agy
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.