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

    Neuronpedia

    INDEX
    Explanations

    references to political events or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    the term "rally" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iencies
    -0.71
     Dictionary
    -0.70
    etheless
    -0.67
    abilities
    -0.64
    missions
    -0.63
    ahime
    -0.62
    ately
    -0.61
    pei
    -0.61
     Fiction
    -0.61
     Leopard
    -0.60
    POSITIVE LOGITS
     rally
    1.13
     rallies
    1.05
    isers
    0.94
    goers
    0.92
     Rally
    0.90
     denouncing
    0.90
     organizer
    0.89
     attendees
    0.89
     organisers
    0.89
     marches
    0.88
    Act Density 0.034%

    No Known Activations