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

    Neuronpedia

    INDEX
    Explanations

    terms related to nondiscrimination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to non-discrimination and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ================
    -0.77
    ======
    -0.75
    Package
    -0.70
     Syndicate
    -0.68
    ppa
    -0.67
    ================================================================
    -0.65
    ularity
    -0.65
     shotguns
    -0.62
    raltar
    -0.62
     Blaze
    -0.62
    POSITIVE LOGITS
    ouble
    1.03
    ocument
    1.01
    oubted
    0.98
    imensional
    0.95
    irect
    0.94
    ere
    0.91
    ynamic
    0.91
    emet
    0.89
    aniel
    0.86
    isc
    0.86
    Act Density 0.009%

    No Known Activations