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

    Neuronpedia

    INDEX
    Explanations

    correlations between different variables or factors

    oai_token-act-pair · gpt-3.5-turbo

    references to correlations in data or research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bold
    -0.77
    gur
    -0.76
    udeb
    -0.74
    nia
    -0.72
    ledge
    -0.72
    arde
    -0.71
    zl
    -0.70
    anas
    -0.70
    frey
    -0.69
    bern
    -0.67
    POSITIVE LOGITS
     coefficient
    1.40
     correlate
    1.25
     correlation
    1.25
     coefficients
    1.19
     correlations
    1.19
     correlated
    0.98
     correlates
    0.97
     correl
    0.94
     linking
    0.82
    relation
    0.81
    Act Density 0.017%

    No Known Activations