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

    Neuronpedia

    INDEX
    Explanations

    mentions of sports groups or teams

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive groups or classifications in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.74
    wards
    -0.70
    LV
    -0.68
    cale
    -0.67
    peria
    -0.66
    Phoenix
    -0.66
    é»Ĵ
    -0.66
    pires
    -0.66
    Bloomberg
    -0.65
    Adv
    -0.64
    POSITIVE LOGITS
    roups
    0.94
    emonium
    0.90
    ativity
    0.88
    tering
    0.86
    mates
    0.84
    ings
    0.83
    ative
    0.82
     mates
    0.79
    leader
    0.78
    members
    0.77
    Act Density 0.050%

    No Known Activations