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

    Neuronpedia

    INDEX
    Explanations

    mentions of political and governmental policies

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.76
    lihood
    -0.75
    ITNESS
    -0.75
     Flavoring
    -0.70
    Vel
    -0.70
    issan
    -0.69
    parts
    -0.68
    ISH
    -0.68
    athan
    -0.68
    brother
    -0.67
    POSITIVE LOGITS
     enacted
    1.02
     governing
    0.93
     implemented
    0.88
     affecting
    0.87
     imposed
    0.85
     restricting
    0.83
     instituted
    0.83
     policies
    0.83
     regulating
    0.81
    hops
    0.80
    Act Density 0.040%

    No Known Activations