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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LLOW
    -0.86
    ']
    -0.71
    ALE
    -0.68
    ETF
    -0.66
    ATHER
    -0.65
     predicate
    -0.63
    ONT
    -0.62
    ðŁĺ
    -0.61
    Adams
    -0.60
    CN
    -0.59
    POSITIVE LOGITS
     Flavoring
    0.86
    ily
    0.78
    bles
    0.77
    kefeller
    0.76
    itatively
    0.70
    geons
    0.70
    down
    0.68
    ging
    0.68
    chard
    0.65
    oug
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.