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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     garn
    -0.69
     MPG
    -0.66
     neut
    -0.64
     augmented
    -0.63
     dexter
    -0.62
     compliment
    -0.61
     antibiotic
    -0.61
    DEP
    -0.60
     owed
    -0.59
     fou
    -0.59
    POSITIVE LOGITS
    ACTED
    0.85
    )).
    0.75
    ]).
    0.69
    ates
    0.68
     STUD
    0.68
    :]
    0.68
    views
    0.68
    orical
    0.68
    kat
    0.66
    Ms
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.