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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    antz
    -0.81
    alf
    -0.77
    minist
    -0.75
    tein
    -0.73
    sburg
    -0.73
    audi
    -0.69
    ende
    -0.68
    ëĭ
    -0.68
    arna
    -0.67
    afa
    -0.66
    POSITIVE LOGITS
    rote
    0.85
     DEFENSE
    0.71
    ccording
    0.68
    rotein
    0.67
     Prec
    0.64
     repe
    0.64
     Probe
    0.62
     Batt
    0.62
     looph
    0.61
    rons
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.