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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bean
    -0.66
     conviction
    -0.65
    Guide
    -0.62
    eva
    -0.62
     pand
    -0.61
    bal
    -0.61
    ATA
    -0.61
    PLA
    -0.60
    odi
    -0.60
    sche
    -0.58
    POSITIVE LOGITS
    owers
    0.83
    ernels
    0.83
    ufact
    0.80
    itect
    0.79
    oteric
    0.76
    ĸļ
    0.75
    rences
    0.72
    ipment
    0.72
    thumbnails
    0.72
    izont
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.