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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     FML
    -0.67
     Lah
    -0.66
     scaff
    -0.65
     Kre
    -0.63
     Playboy
    -0.63
     Lenn
    -0.62
     aisle
    -0.61
    posed
    -0.61
     canvas
    -0.60
     Ceres
    -0.59
    POSITIVE LOGITS
    20439
    0.79
    Reviewer
    0.78
    DIT
    0.75
    в
    0.75
    anian
    0.73
    herty
    0.72
    Favorite
    0.71
    EY
    0.70
    anguage
    0.70
    ashington
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.