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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental policies and their impacts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of governmental or political policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITNESS
    -0.85
    parts
    -0.75
    issan
    -0.74
    lihood
    -0.71
    ISH
    -0.70
    athan
    -0.70
     Sud
    -0.68
    Vel
    -0.67
    ibli
    -0.66
     Flavoring
    -0.65
    POSITIVE LOGITS
     policies
    0.94
     enacted
    0.88
     governing
    0.83
    olicy
    0.80
    hops
    0.80
     implemented
    0.79
     initiatives
    0.76
     pursued
    0.76
     prescriptions
    0.76
    aroo
    0.75
    Act Density 0.025%

    No Known Activations