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

    Neuronpedia

    INDEX
    Explanations

    former political figures and officials, possibly from diverse backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    individuals who have held significant political or governmental positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inis
    -0.78
    Tier
    -0.76
    ophobia
    -0.76
    hops
    -0.75
    ias
    -0.73
    ctica
    -0.73
    pha
    -0.72
    acci
    -0.71
    amn
    -0.70
    ::::::::
    -0.69
    POSITIVE LOGITS
     former
    1.24
     businessman
    1.13
     deputy
    1.09
     actress
    1.03
     others
    1.02
     longtime
    1.00
     fellow
    1.00
     Deputy
    0.99
     novelist
    0.98
    former
    0.98
    Act Density 0.180%

    No Known Activations