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

    Neuronpedia

    INDEX
    Explanations

    political and legislative terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative measures and political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢ
    -0.99
    âĢ
    -0.96
    âĢł
    -0.92
    ¶
    -0.91
     goddamn
    -0.90
     ðŁ
    -0.88
    *:
    -0.85
     +#
    -0.83
     âĺ
    -0.81
     âĪ
    -0.81
    POSITIVE LOGITS
    olicy
    0.66
    avorable
    0.66
    izen
    0.61
    ecided
    0.60
     ideas
    0.60
    okingly
    0.60
     suggestions
    0.59
     idea
    0.58
    avored
    0.58
     possibility
    0.57
    Act Density 1.723%

    No Known Activations