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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to Indian political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific political figure or party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemy
    -0.83
    ilers
    -0.79
    ulsive
    -0.76
    ilation
    -0.75
    imore
    -0.72
    urally
    -0.72
    resses
    -0.70
    urity
    -0.70
    uring
    -0.70
    otaur
    -0.70
    POSITIVE LOGITS
     Lank
    0.82
    ihar
    0.80
    adv
    0.79
    acqu
    0.77
    ¨
    0.75
    vati
    0.74
    ishi
    0.73
    ITY
    0.73
    ¹
    0.72
    ading
    0.70
    Act Density 0.033%

    No Known Activations