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

    Neuronpedia

    INDEX
    Explanations

    references to statistical measures or quantities, particularly related to variance or standard deviation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tenham
    -0.79
     AppColors
    -0.78
     Tamara
    -0.76
     ★
    -0.74
     lepas
    -0.72
     inizio
    -0.71
     spécialisée
    -0.69
     Aps
    -0.68
     Soler
    -0.67
     TSP
    -0.66
    POSITIVE LOGITS
    sigma
    1.62
     σ
    1.49
     sigma
    1.38
    σ
    1.30
     Sigma
    0.90
     Weis
    0.86
     Dogg
    0.84
    SIGMA
    0.82
     Wagner
    0.81
    Mons
    0.78
    Act Density 0.036%

    No Known Activations