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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bye
    -0.67
    uala
    -0.65
     threaded
    -0.61
     wars
    -0.60
    claimed
    -0.59
    Wan
    -0.59
     AAA
    -0.59
    rique
    -0.58
    rage
    -0.58
     Sounders
    -0.57
    POSITIVE LOGITS
    ieri
    0.76
     kcal
    0.76
     âĪĴ
    0.74
    ital
    0.68
    endment
    0.64
     Metatron
    0.64
    eteria
    0.62
    edom
    0.61
    unct
    0.61
     Nadu
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.