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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    protect
    -0.77
    ategory
    -0.74
    onym
    -0.73
    heter
    -0.72
    crime
    -0.71
    agall
    -0.71
    anya
    -0.70
    olon
    -0.70
    ignty
    -0.70
    piracy
    -0.69
    POSITIVE LOGITS
     Klopp
    0.72
     Gallagher
    0.71
     Dull
    0.70
     Eliot
    0.69
     Stro
    0.69
     Wise
    0.68
     excerpts
    0.67
     Kenobi
    0.67
     Blumenthal
    0.64
     Dill
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.