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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    yright
    -0.67
     warehouse
    -0.67
    oubt
    -0.65
    IAS
    -0.64
     Solutions
    -0.64
    slave
    -0.62
     warehouses
    -0.62
    tra
    -0.61
    rica
    -0.61
    erie
    -0.61
    POSITIVE LOGITS
    */(
    0.83
     brill
    0.79
    hess
    0.71
     Nieto
    0.69
    Versions
    0.68
    kered
    0.68
     mathemat
    0.67
     Reborn
    0.66
    imer
    0.65
    Ãĥ
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.