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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to performance enhancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to stability and efficiency metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     originals
    -0.77
    archive
    -0.74
    swick
    -0.71
    artisan
    -0.70
     Ago
    -0.69
    代
    -0.69
     Tanz
    -0.65
    ãĥ³ãĤ¸
    -0.64
    ãĥĦ
    -0.63
     prince
    -0.62
    POSITIVE LOGITS
    factor
    1.07
     inherent
    0.98
     decreases
    0.96
     decreased
    0.90
    effic
    0.89
     affects
    0.86
    Increased
    0.85
     Increases
    0.85
     increases
    0.83
     thresholds
    0.82
    Act Density 0.468%

    No Known Activations