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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    äºĶ
    -0.73
    Jewish
    -0.62
     Lucius
    -0.62
    ledge
    -0.61
     coerc
    -0.61
     Jewish
    -0.60
     Howard
    -0.59
    reek
    -0.59
     Goldberg
    -0.59
    ?),
    -0.58
    POSITIVE LOGITS
    uin
    0.85
    alysed
    0.78
    sem
    0.76
    earchers
    0.76
    utherland
    0.75
    aji
    0.74
    RESULTS
    0.73
    olor
    0.72
    olon
    0.71
    rint
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.