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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legislative actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating categories or groups related to support or benefits for various demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.86
    hao
    -0.79
     sidx
    -0.75
    omi
    -0.75
    clair
    -0.74
    nikov
    -0.71
    chenko
    -0.71
    orbit
    -0.71
    mare
    -0.70
    nil
    -0.69
    POSITIVE LOGITS
     purposes
    1.09
    bidden
    1.08
    aging
    1.07
    gery
    1.05
    gotten
    1.01
     instance
    0.98
     sale
    0.94
    geries
    0.93
    agers
    0.93
    cing
    0.91
    Act Density 0.265%

    No Known Activations