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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements and promises

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their promises or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mages
    -0.84
     ILCS
    -0.71
    allery
    -0.68
     Kali
    -0.64
    ibaba
    -0.62
     mould
    -0.59
     Totem
    -0.59
     Ideal
    -0.58
    DATA
    -0.57
     Quadro
    -0.57
    POSITIVE LOGITS
     Thursday
    1.20
     Tuesday
    1.19
     Wednesday
    1.18
     Friday
    1.18
     Monday
    1.18
     Sunday
    1.13
     yesterday
    1.09
     Saturday
    1.09
     during
    1.04
    Tuesday
    0.98
    Act Density 0.429%

    No Known Activations