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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mascara
    -0.69
     paced
    -0.67
    luster
    -0.67
     diaper
    -0.65
    adelphia
    -0.64
     spice
    -0.60
    Rated
    -0.59
    atche
    -0.59
     mashed
    -0.59
     solder
    -0.59
    POSITIVE LOGITS
     prosecuting
    0.70
    çīĪ
    0.68
    oki
    0.68
     extrad
    0.65
    akeru
    0.65
    uador
    0.64
    uning
    0.64
    raw
    0.63
     reluctant
    0.61
     Sullivan
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.