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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific political figure, Theresa May

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Theresa May."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.83
    anwhile
    -0.82
    alach
    -0.79
    ividual
    -0.77
    venants
    -0.75
    asper
    -0.70
    rador
    -0.70
    oning
    -0.70
    hov
    -0.69
    isode
    -0.68
    POSITIVE LOGITS
     herself
    0.77
     Thatcher
    0.73
     Theresa
    0.72
     Sut
    0.72
    icial
    0.72
     Merkel
    0.71
     Wynne
    0.68
     Devi
    0.68
     Palin
    0.67
     Bee
    0.66
    Act Density 0.024%

    No Known Activations