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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    omore
    -0.72
     Guant
    -0.68
    ucha
    -0.67
    aker
    -0.67
    jer
    -0.66
    oplan
    -0.64
    zh
    -0.63
    erm
    -0.62
    Ãį
    -0.62
    winner
    -0.62
    POSITIVE LOGITS
    LESS
    0.74
    icons
    0.73
     Optimus
    0.68
    ãĥĥãĤ¯
    0.66
    VALUE
    0.64
     Balance
    0.61
    ++++++++
    0.60
     Dust
    0.59
    mble
    0.59
    Matrix
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.