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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Abyssal
    -0.85
    endant
    -0.84
    ategory
    -0.82
    asus
    -0.82
    cens
    -0.80
    ivot
    -0.79
    arius
    -0.79
    agara
    -0.78
    encer
    -0.78
    insula
    -0.78
    POSITIVE LOGITS
    ··
    0.71
     Scottish
    0.67
     Cobra
    0.67
     Meredith
    0.66
     Wolves
    0.65
     Harding
    0.64
     Wilde
    0.62
     Bulldogs
    0.61
     Kyl
    0.60
     Farrell
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.