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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ATA
    -0.71
     ferment
    -0.71
    AMS
    -0.69
    rika
    -0.66
     Russo
    -0.63
     peppers
    -0.61
     dyn
    -0.61
     pepper
    -0.61
    Vo
    -0.61
     knots
    -0.60
    POSITIVE LOGITS
    ulk
    1.08
     care
    0.95
    hess
    0.87
    ãĥŁ
    0.79
    care
    0.78
     Care
    0.72
    perty
    0.72
     misunder
    0.71
    aternity
    0.71
    issance
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.