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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and terms related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events related to power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.94
    lishes
    -0.83
     husbands
    -0.73
     him
    -0.71
     mutual
    -0.69
    alities
    -0.69
    iliar
    -0.68
    acas
    -0.67
    ascript
    -0.66
     Nunes
    -0.66
    POSITIVE LOGITS
     himself
    1.09
     Himself
    0.86
     personally
    0.76
     Majesty
    0.74
     keynote
    0.73
     hect
    0.72
    perse
    0.68
     rall
    0.67
     presiding
    0.66
    panic
    0.63
    Act Density 1.172%

    No Known Activations