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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to performance metrics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative metrics and performance measurements related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.81
    illac
    -0.80
    IRC
    -0.80
    ãĤ¢ãĥ«
    -0.77
    ALD
    -0.75
    uana
    -0.72
    yton
    -0.70
    EY
    -0.70
    inar
    -0.69
    gary
    -0.69
    POSITIVE LOGITS
     indicator
    0.85
     indu
    0.82
     tolerance
    0.80
     ratio
    0.78
     Meter
    0.75
     meter
    0.75
     capability
    0.73
     mismatch
    0.73
     ratings
    0.72
     coefficient
    0.72
    Act Density 0.228%

    No Known Activations