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

    Neuronpedia

    INDEX
    Explanations

    action words related to laws, regulations, and political actions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that relate to political or legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fortunately
    -0.70
     Seym
    -0.63
    doing
    -0.62
    ItemThumbnailImage
    -0.62
    quarters
    -0.61
    likely
    -0.61
    nown
    -0.60
     Variant
    -0.59
    plets
    -0.59
    DragonMagazine
    -0.59
    POSITIVE LOGITS
    enance
    0.97
    igate
    0.77
     him
    0.70
     unpopular
    0.70
    uate
    0.68
    xit
    0.67
     visas
    0.67
     MH
    0.66
     contraceptives
    0.65
     oneself
    0.65
    Act Density 0.383%

    No Known Activations