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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hurricanes
    -0.72
    orce
    -0.66
    powers
    -0.66
    wives
    -0.65
    warning
    -0.64
    match
    -0.62
     spouses
    -0.62
     aux
    -0.62
    fights
    -0.61
    angs
    -0.61
    POSITIVE LOGITS
    za
    0.78
    isky
    0.70
     è£ıè
    0.66
    abin
    0.65
    Äį
    0.64
    ç¥ŀ
    0.64
    %"
    0.64
    ovych
    0.64
    isson
    0.64
    */(
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.