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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ieth
    -0.73
    QUI
    -0.68
    arette
    -0.66
    ÃŃs
    -0.66
    Init
    -0.65
     eb
    -0.65
    Prev
    -0.64
     animate
    -0.64
    :(
    -0.64
     ACTION
    -0.62
    POSITIVE LOGITS
     Dame
    0.75
    picture
    0.72
    hog
    0.68
    Lens
    0.64
    mining
    0.63
    flex
    0.61
    backer
    0.59
     compromises
    0.59
    pict
    0.59
    orting
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.