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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    EMP
    -0.72
    White
    -0.70
     THEN
    -0.70
    Ô
    -0.69
    ãĤ´ãĥ³
    -0.68
    DEC
    -0.68
     NBC
    -0.66
    MED
    -0.66
     Seym
    -0.65
    RAY
    -0.64
    POSITIVE LOGITS
    nir
    0.88
    osuke
    0.83
    mania
    0.69
    stories
    0.69
    iven
    0.69
    ideshow
    0.67
    ravings
    0.67
    aria
    0.66
    \">
    0.66
     Solitaire
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.