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

    Neuronpedia

    INDEX
    Explanations

    themes related to government actions and political criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dime
    -0.70
     favorably
    -0.70
    boro
    -0.70
     utilizing
    -0.69
     totaling
    -0.69
     totaled
    -0.67
     localized
    -0.67
     honors
    -0.64
     UCS
    -0.64
    kees
    -0.63
    POSITIVE LOGITS
    Labour
    1.09
    Shape
    0.99
    Article
    0.98
    Scroll
    0.95
    Britain
    0.93
    Scotland
    0.92
    ³³³³³³³³
    0.88
    England
    0.88
    ³³³³
    0.88
    ³³³³³³³³³³³³³³³³
    0.87
    Act Density 0.379%

    No Known Activations