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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wage
    -0.73
    %);
    -0.71
     compensated
    -0.67
    =]
    -0.67
     spying
    -0.63
     accelerated
    -0.63
    CLUD
    -0.62
     quarters
    -0.62
     Ended
    -0.62
     Aval
    -0.61
    POSITIVE LOGITS
    gard
    0.95
    thora
    0.85
    topic
    0.83
    adr
    0.75
    ugu
    0.74
     corrid
    0.69
    äºĶ
    0.68
    RAW
    0.67
    ctors
    0.67
    leck
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.