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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uve
    -0.67
     ANGEL
    -0.66
     lashes
    -0.65
    amus
    -0.64
    AMY
    -0.64
     disobedience
    -0.61
    anism
    -0.61
     tee
    -0.60
    agle
    -0.60
     pestic
    -0.60
    POSITIVE LOGITS
    arching
    0.67
    mented
    0.64
    angled
    0.63
    wered
    0.62
    led
    0.61
    outine
    0.60
     Tomb
    0.60
    erella
    0.59
    lang
    0.59
    claimer
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.