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

    Neuronpedia

    INDEX
    Explanations

    mentions of politicians and governments, particularly prime ministers and political parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific times in the format of PM

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    keyes
    -0.84
    ¯
    -0.77
    ãĥ³ãĤ¸
    -0.75
     Flavoring
    -0.74
    keye
    -0.74
    itals
    -0.71
    tyard
    -0.69
    ãĤ¨ãĥ«
    -0.67
    come
    -0.66
     Guinness
    -0.66
    POSITIVE LOGITS
    PM
    1.42
    essage
    1.10
    ueller
    1.08
     PM
    0.88
    PLIC
    0.84
     mosqu
    0.84
    ODE
    0.83
    PS
    0.82
    endment
    0.82
    PD
    0.81
    Act Density 0.003%

    No Known Activations