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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pige
    -0.74
     puppies
    -0.73
     kittens
    -0.72
     wolves
    -0.71
     rodents
    -0.70
     bottles
    -0.69
    seekers
    -0.68
    berries
    -0.68
     manuscripts
    -0.66
     Beasts
    -0.66
    POSITIVE LOGITS
    abase
    0.75
    "},
    0.71
    ller
    0.67
    alus
    0.66
    rored
    0.65
    acho
    0.64
    "},{"
    0.64
     Leg
    0.64
    },"
    0.63
     GOODMAN
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.