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

    Neuronpedia

    INDEX
    Explanations

    keywords related to news articles and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the Globe newspaper

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.89
    ivated
    -0.87
    hyde
    -0.84
    amac
    -0.79
    sed
    -0.77
    pill
    -0.75
    inth
    -0.75
    esson
    -0.74
    noon
    -0.74
    swer
    -0.74
    POSITIVE LOGITS
     Globe
    1.01
     Herald
    0.86
     Newspaper
    0.86
     Scotia
    0.83
     bearings
    0.72
     Harbour
    0.71
     Harbor
    0.70
     Beasts
    0.68
     Beast
    0.68
     Wars
    0.67
    Act Density 0.009%

    No Known Activations