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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cheats
    -0.07
    LOOK
    -0.07
     wielding
    -0.07
    我记得
    -0.07
     mime
    -0.07
    ipo
    -0.07
     deriv
    -0.07
    对着
    -0.07
     shootout
    -0.06
    .Route
    -0.06
    POSITIVE LOGITS
    .;
    0.07
     Ab
    0.07
    ų
    0.07
     overnight
    0.07
     indexing
    0.07
    ridged
    0.07
    _eff
    0.07
    คม
    0.07
    폿
    0.07
    .lat
    0.06
    Act Density 0.003%

    No Known Activations