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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    soType
    -0.82
    ulner
    -0.82
    ilit
    -0.76
    essage
    -0.74
    itutional
    -0.73
    ongyang
    -0.72
    abl
    -0.71
    namese
    -0.70
    abus
    -0.69
    atten
    -0.66
    POSITIVE LOGITS
    SPONSORED
    0.78
     numbered
    0.70
     chau
    0.63
     Gou
    0.63
     Examiner
    0.62
    ++++++++++++++++
    0.61
     fav
    0.60
     nud
    0.60
     chemist
    0.59
     smir
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.