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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     subsequ
    -0.73
    raints
    -0.70
    aceutical
    -0.68
    zsche
    -0.67
    CLAIM
    -0.67
     isolate
    -0.66
    iqueness
    -0.66
    kefeller
    -0.65
    ĺħ
    -0.65
     blur
    -0.63
    POSITIVE LOGITS
    mia
    0.88
    wcsstore
    0.75
    awed
    0.74
     yawn
    0.69
    yon
    0.68
     Hispan
    0.68
    anus
    0.67
     brim
    0.66
    hillary
    0.66
    gn
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.