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

    Neuronpedia

    INDEX
    Explanations

    statements related to legislation and political plans

    oai_token-act-pair · gpt-3.5-turbo

    declarative statements about policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -1.08
    æ©
    -0.82
     Indones
    -0.77
     RTX
    -0.74
    airo
    -0.73
    idences
    -0.72
     experien
    -0.72
    DragonMagazine
    -0.71
     photographer
    -0.69
     photographers
    -0.68
    POSITIVE LOGITS
     unconstitutional
    1.30
     unpopular
    1.20
     bipartisan
    1.15
     counterproductive
    1.11
     draconian
    1.08
     riddled
    1.07
     flawed
    1.07
     inco
    1.06
     aimed
    1.06
     discriminatory
    1.06
    Act Density 0.235%

    No Known Activations