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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    specific references to politics and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     UNCLASSIFIED
    -0.86
    SPONSORED
    -0.79
    }.
    -0.79
    lihood
    -0.76
    _.
    -0.73
    >.
    -0.72
    .).
    -0.72
    )).
    -0.71
    :,
    -0.68
    };
    -0.67
    POSITIVE LOGITS
     awoke
    0.71
     unveiled
    0.66
     prepares
    0.66
     has
    0.64
     announced
    0.64
     watchdog
    0.60
     finally
    0.59
     announces
    0.56
     examines
    0.56
     continues
    0.55
    Act Density 0.885%

    No Known Activations