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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gdala
    -0.97
    vu
    -0.78
    Course
    -0.76
     Ll
    -0.76
    chev
    -0.75
    rice
    -0.75
    ":"/
    -0.73
    rollers
    -0.73
    Pad
    -0.72
     Bris
    -0.71
    POSITIVE LOGITS
     ACTIONS
    0.72
     aph
    0.66
     HERO
    0.66
     conglomer
    0.66
     consisted
    0.64
     endorsements
    0.63
     boosters
    0.62
     unions
    0.61
     antibodies
    0.61
     ranks
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.