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

    Neuronpedia

    INDEX
    Explanations

    people's titles, especially in governmental positions

    oai_token-act-pair · gpt-3.5-turbo

    references to political institutions and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dotted
    -0.66
     dots
    -0.64
    plet
    -0.61
    fall
    -0.60
     destruct
    -0.60
     skirm
    -0.59
     jurors
    -0.58
     lanes
    -0.58
    fman
    -0.57
     discrepancy
    -0.56
    POSITIVE LOGITS
     Philippe
    0.89
     Riy
    0.89
     Boris
    0.85
     Nikki
    0.82
     Salman
    0.81
     Denis
    0.80
     Rupert
    0.79
     Ruth
    0.79
     Theresa
    0.77
     Leo
    0.77
    Act Density 0.247%

    No Known Activations