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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Catalyst
    -0.68
    endered
    -0.65
    rex
    -0.62
    gnu
    -0.61
     Fusion
    -0.61
    involved
    -0.61
     affects
    -0.59
    abouts
    -0.59
    result
    -0.59
    perm
    -0.57
    POSITIVE LOGITS
    teen
    0.98
    teenth
    0.89
    İĭ
    0.76
    eenth
    0.75
    aciously
    0.71
     Banner
    0.71
    essee
    0.70
    oooooooo
    0.69
    alion
    0.68
     HUN
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.