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

    Neuronpedia

    INDEX
    Explanations

    references to correlation and covariance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Depp
    -0.70
    #+#
    -0.69
     getB
    -0.68
     huis
    -0.63
     maison
    -0.62
     prost
    -0.62
    austin
    -0.62
    ếc
    -0.61
    iformis
    -0.61
     têtes
    -0.60
    POSITIVE LOGITS
     correlation
    1.27
     correlations
    1.20
     Correlations
    1.08
    Correlation
    1.06
     Correlation
    1.04
    correlation
    1.02
     correlated
    1.00
     correlate
    1.00
    correlated
    0.96
     correl
    0.93
    Act Density 0.028%

    No Known Activations