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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cules
    -0.88
     Soldiers
    -0.74
    fare
    -0.68
     Mistress
    -0.67
    culosis
    -0.66
    peak
    -0.66
     Employees
    -0.66
    farm
    -0.65
    Union
    -0.65
    feet
    -0.63
    POSITIVE LOGITS
    acs
    0.95
    ership
    0.79
    aqu
    0.77
    iah
    0.73
    acco
    0.72
    abeth
    0.71
    acca
    0.71
    ardo
    0.69
    urer
    0.67
    umerable
    0.67
    Act Density 0.035%

    No Known Activations