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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ters
    -0.70
     Swed
    -0.68
    lists
    -0.68
    ãĤ¼
    -0.66
    DonaldTrump
    -0.64
    worm
    -0.63
     Scal
    -0.61
     Collect
    -0.61
     dict
    -0.60
     Erd
    -0.59
    POSITIVE LOGITS
    arij
    0.74
    inness
    0.71
    INESS
    0.70
    acterial
    0.68
    jri
    0.66
    vette
    0.65
    actual
    0.64
    capacity
    0.64
    awei
    0.63
    kefeller
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.