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

    Neuronpedia

    INDEX
    Explanations

    references to Lagrange multipliers and related mathematical concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ellington
    -0.97
    __":
    -0.76
    __':
    -0.72
    ']")
    -0.71
     Svet
    -0.70
     Sze
    -0.69
     Hummel
    -0.69
     houſe
    -0.66
    ...',
    -0.66
    : 
    -0.65
    POSITIVE LOGITS
    Lag
    1.35
     Lag
    1.27
     lag
    1.18
    lag
    1.10
     Lagrange
    0.97
    LAG
    0.95
     LAG
    0.93
     Lagrangian
    0.92
     lags
    0.84
    Laguna
    0.84
    Act Density 0.002%

    No Known Activations